© 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. 112789
    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
    ↵
    -3.75
    </h3>
    -3.42
    e
    -3.17
    </sub>
    -2.86
    </strong>
    -2.84
    曁
    -2.83
    for
    -2.81
    h
    -2.80
    </u>
    -2.61
    s
    -2.61
    POSITIVE LOGITS
    缡
    2.86
     But
    2.77
     लेकिन
    2.56
    \
    2.53
    揠
    2.47
    ᅫ
    2.39
    ’
    2.34
    鬭
    2.34
    蓐
    2.31
    *
    2.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.