© 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. 13261
    Prev
    Next
    INDEX
    Explanations

    java importssql queriesrust modulespython gui code

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

    The neuron strongly activates on decimal number tokens (i.e. floating‐point numerals) in the text.

    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
    ))
    0.59
    )),
    0.57
    vs
    0.57
    ;
    0.56
     Vs
    0.56
    )$$
    0.55
    )}$
    0.55
     versus
    0.55
     fre
    0.52
    说的
    0.52
    POSITIVE LOGITS
    .*;
    1.33
    .{
    1.26
    .*
    1.15
     .{
    1.02
    ::*;
    1.00
     .*
    0.98
     את
    0.97
    ::{
    0.92
     einen
    0.91
     одну
    0.87
    Activations Density 0.000%

    No Known Activations