© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22330
    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
    琲
    -2.50
    If
    -2.50
    should
    -2.30
    𖣔
    -2.30
     itinéraire
    -2.25
    ほとんど
    -2.23
    襌
    -2.23
    他們
    -2.23
    Let
    -2.22
    よろしくお願いします
    -2.20
    POSITIVE LOGITS
    );
    4.78
    家用
    2.55
    ).
    2.55
    k
    2.47
    ))
    2.44
     as
    2.33
    鉝
    2.33
     in
    2.33
     reconoci
    2.33
    </sup>
    2.28
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.