© 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. 8805
    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
    rizona
    -1.77
     Voyez
    -1.73
    ارتمان
    -1.65
    薅
    -1.56
     pascua
    -1.55
     of
    -1.55
     grandeza
    -1.47
    Tembelea
    -1.47
     cannot
    -1.45
    permitAll
    -1.45
    POSITIVE LOGITS
     моего
    1.60
     Наталья
    1.45
    うわ
    1.41
     ")";
    1.38
     }],
    1.38
    здрав
    1.34
    苦笑
    1.34
     Институ
    1.34
     /\.(
    1.32
     моей
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.