© 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. 10-GEMMASCOPE-RES-131K
    7. 101735
    Prev
    Next
    INDEX
    Explanations

    Cadillac, Pontiac, caterpillar, capillary

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

    The neuron fires on mentions of automobile brand names (e.g., Cadillac, Pontiac).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    '
    -2.86
    蹓
    -2.33
     regiões
    -2.23
     пришел
    -2.11
    readFileSync
    -2.08
     jezt
    -2.03
     животные
    -2.02
     mennesker
    -1.98
    ?
    -1.98
     fiscales
    -1.97
    POSITIVE LOGITS
    ’
    3.28
    刹那
    2.55
    数十
    2.39
    霎
    2.39
    鏖
    2.30
    额外
    2.22
    ,’
    2.17
    ’”
    2.17
    T
    2.16
    F
    2.16
    Activations Density 0.003%

    No Known Activations