© 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. 30677
    Prev
    Next
    INDEX
    Explanations

    medium

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

    The neuron consistently activates on numeric tokens or digit sequences (i.e. numbers).

    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
     against
    -0.95
     warehouses
    -0.66
    /...
    -0.66
     elbows
    -0.65
     Familie
    -0.65
     depress
    -0.63
     kicked
    -0.62
     kick
    -0.62
    ("-
    -0.61
    Воз
    -0.61
    POSITIVE LOGITS
     pensive
    0.71
    hoten
    0.71
     Mikel
    0.69
    クロ
    0.68
    IAM
    0.68
     Xy
    0.68
     TSM
    0.67
     Alli
    0.67
     disprove
    0.67
    pension
    0.67
    Activations Density 0.049%

    No Known Activations