© 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. 128408
    Prev
    Next
    INDEX
    Explanations

    armeabi, tomoyo, post, menopausal

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

    programming and technical file elements like domain names, file extensions, and code identifiers.

    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
     in
    -2.27
     with
    -1.77
     of
    -1.63
     them
    -1.59
     where
    -1.48
    1
    -1.48
     any
    -1.46
     based
    -1.44
    玙
    -1.41
     all
    -1.38
    POSITIVE LOGITS
     faſt
    1.71
     creativa
    1.66
     isra
    1.66
     fina
    1.60
     😁
    1.58
    驁
    1.57
     kombi
    1.56
     lorsqu
    1.56
    ANZE
    1.56
     decorativa
    1.55
    Activations Density 0.000%

    No Known Activations