© 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. 16415
    Prev
    Next
    INDEX
    Explanations

    specific terms and titles

    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
     Würde
    -1.08
     vaš
    -1.08
     mainstay
    -1.03
    During
    -1.02
     sisters
    -1.00
     információ
    -0.99
     najbol
    -0.98
    逡
    -0.98
    を読んで
    -0.96
    ὲ
    -0.96
    POSITIVE LOGITS
    <em>
    1.00
    wys
    1.00
     tlie
    0.98
    ,
    0.98
     …
    0.98
    Ž
    0.94
    ­
    0.93
     executes
    0.91
     («
    0.91
    <i>
    0.91
    Activations Density 0.062%

    No Known Activations