© 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. 22-GEMMASCOPE-RES-131K
    7. 104414
    Prev
    Next
    INDEX
    Explanations

    baseball stadium

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

    The neuron fires on technical identifier–style nouns (variable or column names and similar domain‐specific terms, e.g. “month,” “keys,” “values,” “OPERATION,” 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_22/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
     zelfs
    -0.78
    調查
    -0.73
    espa
    -0.71
     ministerio
    -0.71
    тых
    -0.71
    agence
    -0.70
     Jamb
    -0.70
    CHROM
    -0.69
    onio
    -0.69
     zarówno
    -0.69
    POSITIVE LOGITS
    chriften
    0.78
    のではないか
    0.77
    参考に
    0.75
    idal
    0.74
    Fantas
    0.74
    機動
    0.74
     Davy
    0.71
    IENTS
    0.71
    Organizations
    0.71
    hless
    0.70
    Activations Density 0.161%

    No Known Activations