© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13637
    Prev
    Next
    INDEX
    Explanations

    technology and medical outcomes

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

    technical or specialized content, especially mathematical notation, code snippets, and scientific terminology.

    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
     there
    -1.86
     at
    -1.71
     who
    -1.70
     have
    -1.53
     (
    -1.33
    四方
    -1.32
     just
    -1.32
     simply
    -1.31
     S
    -1.30
     B
    -1.30
    POSITIVE LOGITS
     или
    1.54
     vocales
    1.46
    ὢ
    1.38
     kroppen
    1.31
    美味し
    1.28
    หรือ
    1.27
    现在
    1.26
    اااا
    1.25
     melindungi
    1.25
    Its
    1.25
    Activations Density 0.586%

    No Known Activations