© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105583
    Prev
    Next
    INDEX
    Explanations

    file format, event details, code examples

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

    Japanese technical or computing-related terms, particularly those related to code, systems, services, and costs.

    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
    1
    -3.92
    9
    -3.77
    2
    -3.77
    8
    -3.67
     `
    -3.52
    3
    -3.22
    4
    -3.22
    or
    -3.20
    0
    -3.06
    (
    -2.91
    POSITIVE LOGITS
     メニュー
    2.78
    唞
    2.77
    鹉
    2.70
    饃
    2.70
     partici
    2.70
     福袋
    2.63
    ጮ
    2.58
    鹃
    2.56
    歺
    2.53
    獁
    2.50
    Activations Density 0.002%

    No Known Activations