© 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. 100552
    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
     informacje
    -1.16
    lloworld
    -1.08
    beton
    -1.07
     Divulgação
    -1.07
    alne
    -1.05
    sibilità
    -1.04
     projekty
    -1.02
    蹂
    -1.02
     nowy
    -1.01
     게임
    -1.01
    POSITIVE LOGITS
    ;
    1.05
    !
    0.98
    "
    0.91
     “
    0.91
     We
    0.91
     over
    0.88
    ....
    0.88
    /
    0.86
     Buc
    0.85
     How
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.