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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129868
    Prev
    Next
    INDEX
    Explanations

    names with accented characters

    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
    媖
    -2.86
    峮
    -2.70
    Ꮽ
    -2.61
     ส์
    -2.58
    
    -2.56
    ésil
    -2.53
    FUENTES
    -2.52
    نظر
    -2.50
    
    -2.50
    瞇
    -2.48
    POSITIVE LOGITS
    $
    3.66
    *
    3.08
    (
    3.03
    #
    3.00
    “
    2.95
    \
    2.89
    <
    2.70
    T
    2.66
    x
    2.64
    /
    2.61
    Activations Density 0.004%

    No Known Activations