© 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. 127500
    Prev
    Next
    INDEX
    Explanations

    FIG. references

    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
    на
    -2.78
    0
    -2.66
    ↵↵
    -2.64
    :
    -2.30
    Ꮟ
    -2.20
     thinks
    -2.19
     auténtico
    -2.14
    In
    -2.13
     не
    -2.11
     از
    -2.09
    POSITIVE LOGITS
    騭
    2.73
    鬭
    2.61
    埽
    2.59
    linawan
    2.48
    犼
    2.36
    䛗
    2.36
    玙
    2.33
    ῎
    2.33
    鞮
    2.31
    棡
    2.31
    Activations Density 0.003%

    No Known Activations