© 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. 102496
    Prev
    Next
    INDEX
    Explanations

    coffee and CoffeeScript

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

    the word "Coffee" or "CoffeeScript".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     terrific
    -3.00
    ING
    -2.97
    é
    -2.95
    ay
    -2.88
    ꪹ
    -2.81
    ين
    -2.77
    á
    -2.75
    or
    -2.72
    ⩕
    -2.70
    
    -2.67
    POSITIVE LOGITS
     That
    3.03
    Before
    2.75
    𖡼
    2.69
    Also
    2.66
     longstanding
    2.61
    獁
    2.56
    葙
    2.55
    Despite
    2.53
    Since
    2.47
    ープン
    2.45
    Activations Density 0.008%

    No Known Activations