© 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. 68521
    Prev
    Next
    INDEX
    Explanations

    technical questions and how-tos

    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
     where
    -1.74
     the
    -1.66
     включает
    -1.63
     ‘
    -1.58
    ,
    -1.55
    ’
    -1.55
     glittering
    -1.55
     $
    -1.54
     from
    -1.52
     at
    -1.49
    POSITIVE LOGITS
    </tbody>
    1.95
    ↵
    1.84
     juego
    1.80
    ち
    1.70
     marbre
    1.70
    𝐃
    1.69
     новое
    1.66
    <bos>
    1.65
    cionario
    1.65
    asties
    1.63
    Activations Density 0.198%

    No Known Activations