© 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. 101612
    Prev
    Next
    INDEX
    Explanations

    creating intents or commands

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

    function or method calls in programming code, particularly constructor calls and method invocations with parentheses.

    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
     It
    -1.80
     and
    -1.63
     in
    -1.56
     by
    -1.54
     Other
    -1.39
     інші
    -1.35
     genannt
    -1.31
    知ら
    -1.29
     \
    -1.26
     інших
    -1.26
    POSITIVE LOGITS
    袛
    1.70
     +=
    1.52
     the
    1.52
     professionisti
    1.48
    óta
    1.47
    糴
    1.45
     these
    1.43
    ülés
    1.38
     opini
    1.38
    acterísticas
    1.34
    Activations Density 0.045%

    No Known Activations