© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119557
    Prev
    Next
    INDEX
    Explanations

    variable l in math expressions

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

    The neuron fires on single‐letter variable names (e.g. l, o, z, r) in mathematical expressions.

    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
    0
    -2.66
    s
    -1.88
     nossa
    -1.77
    -
    -1.66
    expiresIn
    -1.63
     it
    -1.57
    也要
    -1.57
     nosso
    -1.56
     our
    -1.54
     reconoc
    -1.46
    POSITIVE LOGITS
    );
    
    2.03
    ’
    1.98
    "/>
    
    1.95
    甴
    1.81
    }));
    
    1.77
    ”),
    1.75
    <>());
    1.75
    ();
    
    1.73
    %;
    
    1.70
    )");
    
    1.70
    Activations Density 0.054%

    No Known Activations