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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40433
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ization
    -2.88
    お金
    -2.53
     Они
    -2.50
    翾
    -2.45
    in
    -2.42
    鳚
    -2.42
    ྂ
    -2.41
    に
    -2.33
    }=
    -2.30
     has
    -2.27
    POSITIVE LOGITS
    ing
    2.83
    汌
    2.73
    的で
    2.67
    睒
    2.31
     were
    2.25
    揹
    2.22
     Of
    2.20
    僦
    2.20
    っぷり
    2.19
    鉕
    2.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.