© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39748
    Prev
    Next
    INDEX
    Explanations

    crescent formation and shape names

    np_acts-logits-general · gemini-2.5-flash-lite

    words or shapes that have a curved form, particularly "crescent" or similar curved objects.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    屨
    -3.19
    紲
    -3.11
     ストライプ
    -2.92
     lauded
    -2.86
    
    -2.81
    ఽ
    -2.81
    擼
    -2.75
    퐸
    -2.75
     dát
    -2.72
    
    -2.72
    POSITIVE LOGITS
    ’
    4.25
     unrelenting
    2.84
    ;
    2.78
    ….
    2.73
     \
    2.69
    !!!!!
    2.64
     exquisitely
    2.64
     longstanding
    2.63
    just
    2.61
    …..
    2.61
    Activations Density 0.002%

    No Known Activations