© 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. 21938
    Prev
    Next
    INDEX
    Explanations

    Jai indicating, Iterators, Utrecht, 基础 usage

    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
     of
    -3.02
    .’
    -2.95
    ’，
    -2.53
    。「
    -2.52
    .’”
    -2.45
    欒
    -2.44
     as
    -2.34
    ⡯
    -2.31
    
    -2.30
     from
    -2.22
    POSITIVE LOGITS
    3
    3.75
    7
    3.72
    6
    3.52
    8
    3.19
    5
    3.17
    9
    3.17
    4
    3.17
    色んな
    2.88
    that
    2.86
    2
    2.77
    Activations Density 0.003%

    No Known Activations