© 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. 10-GEMMASCOPE-RES-131K
    7. 105672
    Prev
    Next
    INDEX
    Explanations

    muted followed by sounds

    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
    .”
    -2.34
     humaines
    -2.25
    
    -2.13
    憮
    -2.11
    呖
    -2.09
    蕻
    -2.06
    ꦭ
    -2.06
    Ꮌ
    -2.05
    鯷
    -2.05
     You
    -2.03
    POSITIVE LOGITS
    .
    2.55
    '
    2.34
    muted
    2.23
    </b>
    2.02
    *
    1.98
    我最
    1.98
    the
    1.84
     gescha
    1.79
     выбира
    1.77
    [
    1.73
    Activations Density 0.002%

    No Known Activations