© 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. 85355
    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
    考え方
    -1.02
     Тут
    -1.02
     of
    -0.97
     identical
    -0.97
     weitere
    -0.95
    new
    -0.93
    alisis
    -0.92
     sicherlich
    -0.91
    많
    -0.91
    IDENTIFIED
    -0.90
    POSITIVE LOGITS
     treff
    1.13
     prefeito
    1.05
    &)
    1.02
     novelas
    0.99
    𝑎
    0.98
     cabaña
    0.98
    ąt
    0.96
    Х
    0.96
    atangan
    0.96
    beds
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.