© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48508
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    The neuron chiefly responds to standalone numeric tokens (e.g. page numbers, years, or other numeric citations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beforehand
    -0.74
     unfold
    -0.73
    不管是
    -0.73
     quienes
    -0.71
     before
    -0.70
     incluyendo
    -0.68
     Depart
    -0.68
     aside
    -0.68
     几
    -0.67
     immortality
    -0.67
    POSITIVE LOGITS
    Kill
    0.82
    Half
    0.79
    WILL
    0.79
    Reactor
    0.77
    FIELD
    0.77
    Rapid
    0.76
    Force
    0.76
    ORA
    0.75
     男性
    0.75
    HALF
    0.75
    Activations Density 0.050%

    No Known Activations