© 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. 22-GEMMASCOPE-RES-131K
    7. 68467
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

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

    This neuron detects single-letter variable names (like x, y, a, etc.) 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_22/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
     такие
    -1.27
     deportivas
    -1.20
    neſs
    -1.12
     таких
    -1.11
    嬉しいです
    -1.09
     dieną
    -1.06
    そんな
    -1.06
     également
    -1.03
    後は
    -1.03
    いけない
    -1.02
    POSITIVE LOGITS
    ませて
    1.27
    úrg
    1.02
    triggered
    0.99
     Guter
    0.98
    humanité
    0.98
    href
    0.97
     for
    0.96
    QU
    0.96
    ()]);
    0.94
    articolo
    0.93
    Activations Density 0.021%

    No Known Activations