© 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. 60908
    Prev
    Next
    INDEX
    Explanations

    accented vowels

    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
    ܞ
    -3.30
    เพราะ
    -2.92
    傒
    -2.80
     และ
    -2.78
    giarism
    -2.77
    嚶
    -2.72
    卺
    -2.70
    啬
    -2.69
    
    -2.67
     cozin
    -2.64
    POSITIVE LOGITS
    e
    3.63
    (
    3.44
    /
    3.30
    To
    3.28
    3
    3.19
    ’
    3.17
    1
    3.16
    For
    3.16
    ?
    3.16
    4
    3.11
    Activations Density 0.003%

    No Known Activations