© 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. 30369
    Prev
    Next
    INDEX
    Explanations

    international competitions and the US Open

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

    The neuron selectively activates on numeric tokens—years, dates, statistics, and other multi-digit 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
    декват
    -0.78
     гри
    -0.78
     team
    -0.74
    getTeam
    -0.70
     captain
    -0.70
     on
    -0.70
     lock
    -0.69
     فإن
    -0.69
    حدة
    -0.69
    мах
    -0.69
    POSITIVE LOGITS
    competi
    1.24
     competitors
    1.16
    competition
    1.15
    Competition
    1.14
    Competi
    1.11
     Competition
    1.09
     Competitions
    1.06
     Competi
    1.02
     competition
    1.01
     competitions
    1.01
    Activations Density 0.019%

    No Known Activations