© 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. 6964
    Prev
    Next
    INDEX
    Explanations

    names and technical keywords

    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
    Not in Any Lists

    No Comments

    Negative Logits
    geſ
    -3.08
     firft
    -3.05
    鼇
    -2.92
    iſter
    -2.92
     moft
    -2.78
     绒
    -2.77
     墊
    -2.73
    蚴
    -2.72
     ftate
    -2.72
     男士
    -2.72
    POSITIVE LOGITS
    '
    3.00
     [
    2.98
     {
    2.75
     the
    2.58
     
    2.55
    ”
    2.52
     (
    2.48
    </em>
    2.44
     we
    2.39
     "
    2.31
    Activations Density 0.000%

    No Known Activations