© 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. 22-GEMMASCOPE-RES-131K
    7. 16464
    Prev
    Next
    INDEX
    Explanations

    how questions and explanations

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terá
    -1.00
    試試
    -0.87
     berguna
    -0.84
    PopMatrix
    -0.84
     dikembangkan
    -0.82
     presentó
    -0.81
     dirancang
    -0.80
     bertujuan
    -0.79
     is
    -0.78
    龠
    -0.77
    POSITIVE LOGITS
     इत
    1.17
     get
    1.14
     so
    1.12
    怎么会
    1.01
     become
    0.97
     muun
    0.93
     got
    0.92
     managed
    0.92
     still
    0.90
    atste
    0.90
    Activations Density 0.095%

    No Known Activations