© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67186
    Prev
    Next
    INDEX
    Explanations

    weight and its specifications

    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
    (
    -4.22
    ’
    -3.70
    ”
    -3.47
    x
    -2.94
    u
    -2.89
    …
    -2.84
    ."
    -2.77
    [
    -2.73
     ´
    -2.67
    h
    -2.64
    POSITIVE LOGITS
    ～！
    3.19
     juſ
    3.06
    ！）
    2.78
    齜
    2.72
    
    2.63
    泐
    2.53
    来找
    2.47
    ～～
    2.47
    苁
    2.47
    逡
    2.44
    Activations Density 0.019%

    No Known Activations