© 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. 83983
    Prev
    Next
    INDEX
    Explanations

    presentation title

    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
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -2.81
    这里
    -2.59
    ';
    -2.25
    .'
    -2.25
    .”
    -2.16
    </u>
    -2.14
    鏵
    -2.14
    .,
    -2.14
    ↵↵↵↵↵↵↵↵↵
    -2.13
    <td>
    -2.09
    POSITIVE LOGITS
    歺
    2.13
    翃
    2.09
     gradualmente
    2.02
    ier
    1.97
    😿
    1.95
    ጧ
    1.95
    r
    1.94
     sofistica
    1.93
    sonaro
    1.91
     relativamente
    1.90
    Activations Density 0.011%

    No Known Activations