© 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. 85593
    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
     \&
    -2.23
     &
    -1.95
     and
    -1.75
    \_
    -1.74
     our
    -1.64
     The
    -1.60
     {},
    -1.56
    xxi
    -1.53
     -
    -1.52
    xiii
    -1.48
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.91
     bekym
    1.89
    ↵↵
    1.83
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.76
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.72
    </tr>
    1.67
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.66
     DOMINGO
    1.64
    </h5>
    1.64
     problemet
    1.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.