© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56972
    Prev
    Next
    INDEX
    Explanations

    New Video: "Interview

    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
     enfans
    -0.90
     propia
    -0.89
    providedIn
    -0.88
     canadien
    -0.88
    foreignKey
    -0.88
     Conférence
    -0.86
    rader
    -0.84
    刹那
    -0.84
     subsequently
    -0.83
    bestos
    -0.82
    POSITIVE LOGITS
    這些
    0.94
    这些
    0.87
     mores
    0.86
    cai
    0.86
     anstatt
    0.83
     ハンドバッグ
    0.82
     hieß
    0.82
    zai
    0.81
     sufren
    0.81
     những
    0.80
    Activations Density 0.000%

    No Known Activations