© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112365
    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
     people
    -1.08
    f
    -0.99
     creates
    -0.98
    Now
    -0.98
    麼
    -0.93
    現實
    -0.92
    a
    -0.92
    in
    -0.91
    N
    -0.91
     now
    -0.89
    POSITIVE LOGITS
     pesso
    1.18
     mús
    1.16
     pongo
    1.14
    蛱
    1.14
    וך
    1.13
     コンパクト
    1.13
     europé
    1.10
     剧照
    1.10
     garan
    1.10
     MIK
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.