© 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. 44384
    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
    ↵
    -1.00
    ),
    -0.96
    のよ
    -0.95
     of
    -0.93
    </em>
    -0.91
     host
    -0.91
    ],
    -0.90
     More
    -0.89
     held
    -0.86
    ׁ
    -0.83
    POSITIVE LOGITS
    啻
    1.26
    1.06
     klant
    1.05
     Eilish
    1.05
     OGSÅ
    1.05
    ischem
    1.02
    Ꮵ
    1.00
     cible
    1.00
    🏌
    0.98
    ܜ
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.