© 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. 13959
    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
    にかく
    -0.96
     pretože
    -0.93
    mittances
    -0.92
     QLD
    -0.91
     gobiernos
    -0.91
    sugges
    -0.90
     próprios
    -0.90
     verdadera
    -0.90
     phénomène
    -0.90
    opération
    -0.89
    POSITIVE LOGITS
     réflé
    1.04
    来自
    1.02
     yyr
    1.02
    𓆜
    0.96
    )')
    0.96
    )}}
    0.94
     hagan
    0.94
    }})
    0.93
    <td>
    0.92
    PRINT
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.