© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64546
    Prev
    Next
    INDEX
    Explanations

    closing punctuation then opening brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    <u>
    -0.98
     is
    -0.97
    <em>
    -0.96
    the
    -0.94
     nazis
    -0.94
    //
    -0.93
    .
    -0.90
    '
    -0.88
    在
    -0.88
    ñan
    -0.87
    POSITIVE LOGITS
     that
    1.23
     it
    1.22
     fronteras
    1.16
     or
    1.10
     negociaciones
    1.03
     cabezas
    1.02
     elegancia
    1.02
     textures
    1.02
     its
    1.02
     materiais
    1.01
    Activations Density 0.006%

    No Known Activations