© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3306
    Prev
    Next
    INDEX
    Explanations

    developers and their tools

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

    The neuron detects numeric tokens with decimal points (i.e. floating‐point numbers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    रिट
    0.60
     بالج
    0.59
    %$$
    0.55
    Voids
    0.55
     dž
    0.54
     UserDefaults
    0.54
    谕
    0.54
    >]
    0.53
    errno
    0.53
    傾
    0.53
    POSITIVE LOGITS
     anyone
    0.59
     niemand
    0.59
     하나
    0.58
     me
    0.55
     ერთი
    0.55
    It
    0.54
    As
    0.54
     everyone
    0.54
    没人
    0.53
     кого
    0.52
    Activations Density 0.002%

    No Known Activations