© 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. 128837
    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
    へ行
    -1.85
    凄い
    -1.54
    Elő
    -1.46
    に行って
    -1.45
     навіть
    -1.44
     mostró
    -1.41
    咿
    -1.41
    さぁ
    -1.40
    かなり
    -1.39
    ICAGO
    -1.38
    POSITIVE LOGITS
     on
    1.94
     from
    1.71
     with
    1.50
     our
    1.24
     during
    1.23
     more
    1.22
     at
    1.21
     vacancies
    1.21
     occasione
    1.20
     its
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.