© 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. 22877
    Prev
    Next
    INDEX
    Explanations

    Pal, Elizabeth, Q

    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
     you
    -2.48
     to
    -1.63
     (...)
    -1.59
    すべき
    -1.55
    име
    -1.55
    Вт
    -1.50
    thello
    -1.48
    承担
    -1.48
     cuando
    -1.47
     gegenwär
    -1.46
    POSITIVE LOGITS
     —
    2.02
    4
    1.90
    3
    1.56
    Where
    1.55
    ‌های
    1.51
     samma
    1.45
    iz
    1.45
    ities
    1.44
     một
    1.43
    ’，
    1.42
    Activations Density 0.019%

    No Known Activations