© 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. 85516
    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
    甗
    -2.25
    鶿
    -2.22
    籏
    -2.06
    mpagne
    -2.03
    慙
    -2.00
    嚨
    -1.90
    嫆
    -1.87
    たまに
    -1.83
     imprimer
    -1.82
    翃
    -1.82
    POSITIVE LOGITS
     they
    2.20
    </strong>
    2.16
    </em>
    2.05
     was
    1.92
     For
    1.88
     für
    1.87
     will
    1.80
     a
    1.78
    。」
    1.77
     FOR
    1.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.