© 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. 119885
    Prev
    Next
    INDEX
    Explanations

    start_url, start_date, start_check, start_process, start_worker

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

    the underscore character immediately following words like "start" in variable names, URLs, and code identifiers.

    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
     pacar
    -1.88
    描く
    -1.80
    ܊
    -1.73
    和她
    -1.72
    葑
    -1.66
    描いた
    -1.66
     \&
    -1.66
    皤
    -1.63
    {
    -1.63
     juga
    -1.63
    POSITIVE LOGITS
    .”
    2.39
    ;
    2.28
    );
    2.05
     */
    2.03
    ));
    1.87
     worrying
    1.87
    ];
    1.85
    .’’
    1.84
    }
    1.80
    反抗
    1.79
    Activations Density 0.028%

    No Known Activations