© 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. 7374
    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
    〝
    -0.99
    ops
    -0.96
     ‚
    -0.89
    挙げ
    -0.89
     ferv
    -0.86
    OBJETIVO
    -0.86
    思い出
    -0.85
     sólo
    -0.85
     fearing
    -0.84
    とこ
    -0.84
    POSITIVE LOGITS
    bietet
    0.98
    onViewCreated
    0.96
    mittelt
    0.90
     sporo
    0.90
     فهي
    0.89
    legte
    0.88
     podp
    0.88
     doká
    0.87
    쭈
    0.86
    unset
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.