© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128451
    Prev
    Next
    INDEX
    Explanations

    import statements

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

    The neuron specifically flags import statements that end with the class name “Client,” activating on the “Client” token (and its trailing semicolon) in such lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     a
    -2.23
     /
    -1.94
     all
    -1.87
     at
    -1.86
     most
    -1.73
     â
    -1.69
     an
    -1.64
     sufre
    -1.57
     only
    -1.53
    厕所
    -1.52
    POSITIVE LOGITS
     of
    2.36
    </h3>
    2.28
     definitivamente
    1.91
    哢
    1.88
    <bos>
    1.83
     proveniente
    1.77
     evidentemente
    1.73
    ↵↵
    1.73
     provocando
    1.72
     ";
    
    1.69
    Activations Density 0.066%

    No Known Activations