© 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. 84732
    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
    Ie
    -1.16
    䛗
    -1.09
     autunno
    -1.05
     dieß
    -1.04
    represents
    -1.03
    墊
    -1.02
    ︕
    -0.99
     Monza
    -0.98
     bagno
    -0.98
    igten
    -0.97
    POSITIVE LOGITS
     using
    1.29
     including
    1.27
     it
    1.11
     used
    1.02
     is
    1.00
     both
    0.98
    %
    0.97
     reservado
    0.96
    ’
    0.94
     helping
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.