© 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. 130564
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
     is
    -2.61
     zweite
    -2.39
     gemeinsame
    -2.34
     tiefe
    -2.16
     spezielle
    -2.14
    н
    -2.14
     whirl
    -2.11
    \
    -2.09
    (
    -2.09
    เพราะ
    -2.09
    POSITIVE LOGITS
    ).
    3.73
    </strong>
    3.34
    as
    3.02
    趼
    2.70
    te
    2.69
    觏
    2.66
    釓
    2.45
    ࿙
    2.36
     boty
    2.31
    他自己
    2.30
    Activations Density 0.093%

    No Known Activations