© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7033
    Prev
    Next
    INDEX
    Explanations

    version numbers

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

    The neuron fires on numeric version identifiers (decimal numbers) typically used to denote software or document version numbers.

    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
    ys
    0.38
     paced
    0.38
    s
    0.38
    ind
    0.37
    Velocity
    0.37
    ES
    0.36
    Diss
    0.36
    Appro
    0.36
    Absorption
    0.35
    ↵↵
    0.35
    POSITIVE LOGITS
    スマートフォン
    0.45
     mochila
    0.44
     kanya
    0.44
     versiones
    0.43
    usingCamera
    0.43
     Installing
    0.43
    parvec
    0.43
     fratello
    0.43
     currant
    0.42
    cego
    0.42
    Activations Density 0.004%

    No Known Activations