© 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. 87043
    Prev
    Next
    INDEX
    Explanations

    that introduces a clause

    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
     only
    -2.83
     if
    -2.75
     also
    -2.39
     quite
    -2.27
     first
    -2.23
     of
    -2.23
     very
    -2.14
     greatly
    -2.13
     more
    -2.11
     just
    -2.09
    POSITIVE LOGITS
    ଃ
    1.93
     pérd
    1.91
    跸
    1.90
    嗵
    1.83
    ícias
    1.75
     manières
    1.73
    鲵
    1.73
    鲼
    1.68
    tains
    1.65
    
    1.65
    Activations Density 0.043%

    No Known Activations