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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109756
    Prev
    Next
    INDEX
    Explanations

    permissions and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Shat
    -0.73
    randn
    -0.69
    tella
    -0.68
     partid
    -0.66
     Terri
    -0.66
    تے
    -0.66
    odon
    -0.66
     Beal
    -0.63
    ianti
    -0.63
     Rav
    -0.62
    POSITIVE LOGITS
    dyr
    0.72
    いきましょう
    0.70
    тивное
    0.68
    ͢
    0.67
     Agora
    0.67
    polling
    0.66
    holic
    0.66
    cripción
    0.66
     Hiller
    0.66
    agaimana
    0.65
    Activations Density 0.085%

    No Known Activations