© 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. 24-GEMMASCOPE-2-RES-16K
    7. 823
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially floating-point numbers (e.g. decimals)—often appearing in parentheses.

    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
    ise
    0.48
    (!
    0.48
     sliders
    0.46
     nbsp
    0.46
    ((
    0.45
    isieren
    0.44
     dampers
    0.44
    (&(
    0.43
    (_,
    0.43
    ić
    0.43
    POSITIVE LOGITS
    pictured
    0.73
    formerly
    0.73
    including
    0.71
    also
    0.64
    from
    0.63
    %),
    0.63
    which
    0.61
    aka
    0.59
    hereinafter
    0.59
    англ
    0.58
    Activations Density 0.191%

    No Known Activations