© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86414
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    The neuron strongly activates on single‐letter mathematical variable tokens (like u, a, r, k, c, etc.) within algebraic or arithmetic 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
     it
    -2.05
     of
    -1.97
     by
    -1.77
     or
    -1.59
     at
    -1.52
    ”（
    -1.46
    ”。
    -1.43
    枚目
    -1.43
    ,”
    -1.40
     even
    -1.34
    POSITIVE LOGITS
     Envío
    1.88
    licopter
    1.81
     Accesorios
    1.73
     Características
    1.66
     Viene
    1.64
     Apenas
    1.63
     нынеш
    1.63
     Obtén
    1.63
     Teléfono
    1.63
     Ubicación
    1.62
    Activations Density 0.166%

    No Known Activations