© 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. 44625
    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
    .
    -1.16
     sè
    -0.93
    ǫ
    -0.92
     deel
    -0.87
     thai
    -0.85
     Romanian
    -0.85
     Wro
    -0.84
     BLA
    -0.83
    崛
    -0.83
     gj
    -0.83
    POSITIVE LOGITS
     manifestazione
    1.15
     економі
    1.09
     decorazione
    1.08
     τελευτα
    1.08
     trasmissione
    1.05
     presentazione
    0.99
    憮
    0.99
     accompany
    0.95
     mancanza
    0.95
    núť
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.