© 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. 112622
    Prev
    Next
    INDEX
    Explanations

    code blocks with math or logic

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

    closing parentheses in mathematical expressions or code.

    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
     sogenannte
    -1.45
     appelé
    -1.45
     what
    -1.34
    mathop
    -1.33
     sogenannten
    -1.33
    所谓的
    -1.31
    んびり
    -1.31
     soportes
    -1.27
    yup
    -1.27
    ：……
    -1.27
    POSITIVE LOGITS
     until
    1.49
    𝘖
    1.34
    ração
    1.34
    任何
    1.32
    här
    1.29
    You
    1.27
     резулта
    1.27
    uberge
    1.27
    tku
    1.27
     but
    1.26
    Activations Density 0.006%

    No Known Activations