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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 834
    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
    B
    -1.98
     -
    -1.82
    そうですが
    -1.69
    S
    -1.63
     pracow
    -1.56
    ázaro
    -1.56
    U
    -1.54
     übri
    -1.53
    ),
    -1.53
    );
    -1.51
    POSITIVE LOGITS
     bacté
    1.84
    ⚋
    1.65
     riesce
    1.63
    zzazione
    1.58
     dreaded
    1.58
     résistance
    1.55
     comer
    1.53
    筇
    1.52
     importante
    1.52
    在住
    1.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.