© 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. 41601
    Prev
    Next
    INDEX
    Explanations

    computer graphics and geometry

    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
    ,”
    -2.58
    ↵
    -2.48
    Seperti
    -2.36
     []
    -2.27
    \
    -2.17
    灩
    -2.14
     ६
    -2.14
    ｢
    -2.09
    的人都
    -2.06
     dizzy
    -2.02
    POSITIVE LOGITS
     erhi
    2.44
     were
    2.27
    '
    2.23
    derdag
    2.20
     You
    2.17
     membri
    2.16
    羕
    2.11
    厹
    2.08
    getting
    2.08
    儅
    2.05
    Activations Density 0.015%

    No Known Activations