© 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. 71917
    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
    ↵
    -3.11
     juſ
    -3.06
    辚
    -3.05
    ፨
    -3.03
    姈
    -2.94
     Dinas
    -2.92
     !!!!
    -2.92
    ⏑
    -2.86
     WIL
    -2.81
     ſever
    -2.77
    POSITIVE LOGITS
     with
    3.56
     as
    3.33
     although
    3.33
     after
    3.33
     What
    3.27
     When
    3.22
     at
    3.20
     because
    3.19
     before
    3.17
     for
    3.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.