© 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. 43173
    Prev
    Next
    INDEX
    Explanations

    disregard or

    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
    嵙
    -2.47
    婼
    -2.41
     OGSÅ
    -2.39
    derdag
    -2.38
     ovat
    -2.36
    劼
    -2.31
    ᝢ
    -2.30
    尪
    -2.22
    鉭
    -2.22
    lusconi
    -2.20
    POSITIVE LOGITS
    ↵
    2.86
    ：“
    2.50
    on
    2.41
    “
    2.27
    ,“
    2.19
     unſ
    2.17
    $,
    2.13
    、“
    2.09
    噌
    2.08
    ，
    2.05
    Activations Density 0.005%

    No Known Activations