© 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. 86264
    Prev
    Next
    INDEX
    Explanations

    baking

    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
    嫆
    -3.30
    
    -3.13
    ’
    -2.91
    ⢅
    -2.64
    厶
    -2.61
    錳
    -2.58
    僦
    -2.52
    不过是
    -2.50
     izquierdo
    -2.47
    轳
    -2.42
    POSITIVE LOGITS
    i
    3.52
    剮
    3.06
    a
    2.84
     рукой
    2.67
    o
    2.66
    駢
    2.39
    F
    2.34
    蟊
    2.33
    e
    2.20
    🢐
    2.20
    Activations Density 0.001%

    No Known Activations