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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8732
    Prev
    Next
    INDEX
    Explanations

    ethical, legal, safety

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

    The neuron fires on long, formal, domain‐specific nouns (e.g. “typographical,” “constitutional,” “cultural,” “medical”).

    oai_token-act-pair · o4-miniTriggered 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
     জন্য
    0.81
    '.
    0.80
     জন্যে
    0.71
    No
    0.68
    한다
    0.67
    ,'
    0.66
    ¿
    0.66
    Cor
    0.65
    Nell
    0.65
    a
    0.65
    POSITIVE LOGITS
     behavioral
    0.67
     Midwestern
    0.67
     иных
    0.65
     proximate
    0.64
     جب
    0.63
    ogenic
    0.62
     recessive
    0.62
    rische
    0.62
    StringSet
    0.61
     informational
    0.61
    Activations Density 0.481%

    No Known Activations