© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107307
    Prev
    Next
    INDEX
    Explanations

    names following 'rookie' or 'young'

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

    The neuron primarily activates on numeric tokens—especially large numbers—used as sports statistics (points, scores, years, jersey numbers, etc.).

    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
     الإلكتر
    -0.92
     pétrole
    -0.89
    lussen
    -0.84
     PackageManager
    -0.83
    ÇO
    -0.79
    Jiang
    -0.79
    éges
    -0.79
    👣
    -0.79
     japoneses
    -0.78
    endency
    -0.77
    POSITIVE LOGITS
    ukasz
    0.81
     taboo
    0.75
    െ
    0.73
     دیواری
    0.72
     Satoshi
    0.71
    userRole
    0.71
    大神
    0.71
     erfolgreich
    0.69
     odpowiedzi
    0.69
     比較
    0.68
    Activations Density 0.058%

    No Known Activations