© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 32952
    Prev
    Next
    INDEX
    Explanations

    awards and nominations

    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
     soyez
    -0.92
     musique
    -0.91
    様です
    -0.90
     недавно
    -0.89
     ]);
    -0.89
     rivière
    -0.88
     contentType
    -0.88
    комплект
    -0.87
    号線
    -0.85
     ];
    -0.84
    POSITIVE LOGITS
    oczes
    1.27
    >-
    0.93
    馳走
    0.90
    \}}
    0.89
    そして
    0.84
    jø
    0.84
    igation
    0.84
     and
    0.84
    auces
    0.83
    abinieri
    0.83
    Activations Density 0.007%

    No Known Activations