© 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. 10-GEMMASCOPE-RES-131K
    7. 38578
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by attribution

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    It
    -2.52
    ),
    -2.16
    If
    -2.06
    <blockquote>
    -1.99
    <h3>
    -1.96
     It
    -1.95
    }
    -1.91
    The
    -1.88
    %;
    -1.88
    %;
    -1.85
    POSITIVE LOGITS
     sprawie
    2.00
     of
    1.97
     読む
    1.94
    皤
    1.85
    潆
    1.83
     muhimu
    1.77
     zajíma
    1.77
     déchir
    1.75
    囡
    1.73
    皝
    1.70
    Activations Density 0.028%

    No Known Activations