© 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. 3030
    Prev
    Next
    INDEX
    Explanations

    code examples

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

    The neuron strongly activates on numeric literals (especially floating‐point numbers or digit sequences) in code or data.

    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
     +=
    0.43
     -=
    0.42
     sprintf
    0.41
    ONENT
    0.41
    ὸς
    0.39
    ';"+
    0.39
    ην
    0.39
    sprintf
    0.38
     >>=
    0.38
    umsal
    0.38
    POSITIVE LOGITS
     ,
    0.50
     compre
    0.47
     .,
    0.46
     एकज
    0.46
     unrecognizable
    0.45
     pleads
    0.45
     proff
    0.44
     desesper
    0.44
     permasalahan
    0.44
     FRG
    0.43
    Activations Density 0.000%

    No Known Activations