© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3823
    Prev
    Next
    INDEX
    Explanations

    temperature, texture, or physical state

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on the names of popular month‐long or promotional campaigns (e.g. “Dry January,” “Plastic Free July,” “Dry February”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words related to cleanliness, purity, or absence of moisture/substances (such as "dry," "clear," "white," "clean," "free").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    adjectives that denote descriptive states or degrees, especially those about physical/health conditions, cleanliness/clarity, temperature, or abstinence/absence.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ް
    0.74
    Alumno
    0.72
     کئی
    0.68
     utilized
    0.66
     Alguns
    0.66
     utilizz
    0.66
     Ecco
    0.65
    Hora
    0.64
     درسنا
    0.64
    RFID
    0.64
    POSITIVE LOGITS
    ness
    0.95
     ≠
    0.70
    igs
    0.70
    <0x9C>
    0.64
    heit
    0.63
     bờ
    0.63
     pigs
    0.63
    nesses
    0.61
     cytoplasm
    0.61
    ening
    0.60
    Activations Density 0.008%

    No Known Activations