© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119602
    Prev
    Next
    INDEX
    Explanations

    form encoding and multipart data

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

    form data and multipart content type specifications in HTTP requests and web programming contexts.

    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
     these
    -1.79
     those
    -1.77
    g
    -1.69
     that
    -1.67
    );
    -1.53
    These
    -1.48
    這些
    -1.42
    <
    -1.42
     theses
    -1.36
     about
    -1.35
    POSITIVE LOGITS
    完成です
    1.58
    彼女の
    1.37
     coté
    1.35
    risation
    1.35
    ᥀
    1.34
    茈
    1.34
     négo
    1.33
    ጢ
    1.32
     dégust
    1.31
    んですけど
    1.30
    Activations Density 0.011%

    No Known Activations