© 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. 71083
    Prev
    Next
    INDEX
    Explanations

    Gerard, Kamal, chromatogram, glutathione

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

    proper nouns and scientific/chemical compound terms.

    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
    雠
    -2.63
    ຼ
    -2.61
    㩒
    -2.53
    闥
    -2.42
    ㋛
    -2.41
    囌
    -2.34
    鶘
    -2.34
     จะ
    -2.31
    櫈
    -2.27
    $
    -2.25
    POSITIVE LOGITS
    ↵
    2.92
    o
    2.83
     In
    2.66
     somber
    2.50
     Ironically
    2.39
     dwindling
    2.31
    y
    2.28
    ت
    2.28
     Originally
    2.27
     burgeoning
    2.23
    Activations Density 0.006%

    No Known Activations