© 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. 85935
    Prev
    Next
    INDEX
    Explanations

    allegations and accusations

    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
    i
    -1.97
    I
    -1.95
    י
    -1.90
    ي
    -1.70
    ności
    -1.70
     домой
    -1.70
    。　
    -1.68
    茄
    -1.66
    。　　
    -1.63
    (
    -1.62
    POSITIVE LOGITS
    色んな
    1.71
    少しでも
    1.70
     acusa
    1.66
    ↵
    1.65
    色々と
    1.62
    Caracteristici
    1.61
     Při
    1.60
     historische
    1.58
     verminder
    1.57
    ῞
    1.56
    Activations Density 0.028%

    No Known Activations