© 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. 34-GEMMASCOPE-RES-131K
    7. 103934
    Prev
    Next
    INDEX
    Explanations

    solve algebraic equations

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

    The neuron activates on individual numeral characters (digits) 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_34/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
    jshint
    -0.92
     said
    -0.92
    ()=>{
    -0.89
    ⚢
    -0.88
     avanzada
    -0.88
     Antrag
    -0.85
     which
    -0.84
     says
    -0.84
    嫵
    -0.84
     مشين
    -0.83
    POSITIVE LOGITS
     seba
    0.96
    Después
    0.94
     parlament
    0.92
    verstanden
    0.92
    $};
    0.91
    гъл
    0.90
     caricatura
    0.90
     tonel
    0.90
    "#
    0.89
     esses
    0.88
    Activations Density 0.002%

    No Known Activations