© 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. 67184
    Prev
    Next
    INDEX
    Explanations

    octopus, creatinine, CNT

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

    references to octopuses and scientific terminology related to creatinine levels.

    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
    7
    -2.94
    m
    -2.81
    地说道
    -2.80
    是啊
    -2.78
    a
    -2.61
    4
    -2.55
    );
    -2.55
    ing
    -2.50
     zuhause
    -2.50
    ان
    -2.31
    POSITIVE LOGITS
    翃
    2.48
     ulub
    2.45
     unwise
    2.42
     informací
    2.31
     meek
    2.30
    end
    2.27
    せよ
    2.23
    ENCIAS
    2.23
    可以让
    2.23
    这样一个
    2.22
    Activations Density 0.012%

    No Known Activations