© 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. 105513
    Prev
    Next
    INDEX
    Explanations

    private attributes and special methods

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

    double underscores (`__`) in code, typically indicating special methods or private attributes in programming languages.

    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
    镡
    -2.64
    鳢
    -2.52
    螣
    -2.34
    蔸
    -2.28
    晛
    -2.27
    塍
    -2.23
    櫪
    -2.20
    鉝
    -2.20
    ୮
    -2.19
    
    -2.14
    POSITIVE LOGITS
    4
    3.23
    '
    3.17
    5
    3.09
    7
    3.00
    This
    2.95
    2
    2.95
    ほんと
    2.78
    3
    2.73
    .__
    2.69
    The
    2.59
    Activations Density 0.001%

    No Known Activations