© 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. 8319
    Prev
    Next
    INDEX
    Explanations

    variable declaration followed by assignment/check

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

    The neuron fires strongly on exactly three‐character tokens (e.g. “err” or “url”).

    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
    (((
    0.69
     пя
    0.64
     регистрации
    0.63
     করিবে
    0.62
    lastval
    0.61
     остан
    0.59
     jego
    0.58
    ((*
    0.58
     jeśli
    0.58
     (((
    0.57
    POSITIVE LOGITS
     nicht
    0.69
     is
    0.68
     ikke
    0.65
     didn
    0.64
     nisu
    0.59
     are
    0.58
     Ex
    0.58
     är
    0.57
     Coaches
    0.57
     in
    0.56
    Activations Density 0.000%

    No Known Activations