© 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. 103364
    Prev
    Next
    INDEX
    Explanations

    sending messages and reading files

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

    function names or identifiers related to sending messages or reading files in 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
    就
    -2.94
     rufen
    -2.50
    是
    -2.47
     整
    -2.47
     Would
    -2.44
    or
    -2.44
    ；
    -2.38
    内容
    -2.34
     前
    -2.33
    其
    -2.33
    POSITIVE LOGITS
    珰
    3.77
    雠
    3.17
    Ꝑ
    2.95
    苼
    2.89
    葑
    2.83
     การ์ตูน
    2.67
    Ꮀ
    2.67
    ٶ
    2.61
     betekent
    2.58
    疍
    2.58
    Activations Density 0.001%

    No Known Activations