© 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. 84834
    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
    并在
    -1.20
     Anſ
    -1.11
     –
    -1.11
    :?
    -1.10
     garan
    -1.09
    ⸮
    -1.06
    ographically
    -1.06
     also
    -1.05
     diharapkan
    -1.04
     testamento
    -1.04
    POSITIVE LOGITS
    </b>
    1.30
     ürünleri
    1.18
     strenuous
    1.16
     geeigne
    1.12
     detrás
    1.10
     بشه
    1.09
    5
    1.06
     stint
    1.05
     boast
    1.05
     às
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.