© 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. 43195
    Prev
    Next
    INDEX
    Explanations

    mathematical variables or symbols

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

    The neuron consistently lights up on isolated single-letter mathematical identifiers (e.g. f, x) in the LaTeX‐style formulae.

    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
    ſſen
    -1.80
    鹩
    -1.74
     Reſ
    -1.68
     Inſ
    -1.67
    力
    -1.57
     apartament
    -1.56
    ——”
    -1.55
     手绘
    -1.55
    งิน
    -1.53
     unſ
    -1.53
    POSITIVE LOGITS
     may
    1.84
    9
    1.81
     can
    1.77
    7
    1.77
     might
    1.76
     but
    1.70
     so
    1.68
     at
    1.68
     could
    1.68
    1
    1.66
    Activations Density 0.029%

    No Known Activations