© 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. 114177
    Prev
    Next
    INDEX
    Explanations

    search for

    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
    橚
    -2.00
    .
    -1.91
    These
    -1.91
     ligeramente
    -1.76
     <",
    -1.74
     :");
    -1.70
    Ꮂ
    -1.70
     sata
    -1.68
    на
    -1.64
    茲
    -1.64
    POSITIVE LOGITS
     a
    3.31
    谖
    2.20
     an
    1.86
    他的
    1.84
    おわりに
    1.80
     suuri
    1.75
     where
    1.73
     gesellschaft
    1.72
    逖
    1.72
     in
    1.70
    Activations Density 0.016%

    No Known Activations