© 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. 68646
    Prev
    Next
    INDEX
    Explanations

    copyright/license text

    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
     participó
    -1.91
    "
    -1.84
     sufrió
    -1.84
     anunció
    -1.80
     terminó
    -1.78
    火的
    -1.73
     decidió
    -1.70
    ጵ
    -1.66
     entró
    -1.66
    男主
    -1.63
    POSITIVE LOGITS
    ”
    2.02
    ).
    1.94
     cuaca
    1.84
    ’
    1.76
    —”
    1.75
     クー
    1.71
     (“
    1.71
     päivä
    1.70
    d
    1.70
    ielles
    1.66
    Activations Density 0.017%

    No Known Activations