© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12651
    Prev
    Next
    INDEX
    Explanations

    is followed by the

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

    The neuron activates on floating‐point numeric constants (numbers with decimal points).

    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_31_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
    \,
    0.60
    \;
    0.59
     \;
    0.57
    OfString
    0.57
    Mr
    0.56
    {
    0.55
    Sketch
    0.54
    W
    0.53
     pate
    0.53
    ^{
    0.52
    POSITIVE LOGITS
     miscellaneous
    0.66
     frequência
    0.63
     reputation
    0.60
     muque
    0.60
    agd
    0.59
     ucap
    0.57
     campagne
    0.57
     iedere
    0.57
     অজানা
    0.56
    比賽
    0.55
    Activations Density 0.000%

    No Known Activations