© 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. 58337
    Prev
    Next
    INDEX
    Explanations

    Upp names and code contexts

    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
    *
    -3.42
    (
    -3.28
    ?
    -3.05
    ',
    -3.00
     This
    -2.97
    e
    -2.88
    ...
    -2.86
    T
    -2.84
    The
    -2.80
    Y
    -2.70
    POSITIVE LOGITS
    茔
    2.81
    跎
    2.67
    踽
    2.64
    窠
    2.48
     خانگی
    2.47
    providedIn
    2.42
    勗
    2.42
    泅
    2.41
    馓
    2.39
     cũng
    2.31
    Activations Density 0.005%

    No Known Activations