© 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. 130010
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and notation

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

    The neuron responds to single‐letter mathematical variable tokens (like “t,” “n,” “p,” “j,” etc.) in 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
     głównie
    -2.11
    ⦊
    -1.77
    uebas
    -1.73
     its
    -1.72
     präsenti
    -1.66
     stellte
    -1.61
     ließ
    -1.60
     chiefly
    -1.60
     aynı
    -1.55
     moléculas
    -1.55
    POSITIVE LOGITS
    8
    2.19
    7
    2.16
    6
    2.08
    2
    1.98
    If
    1.80
    9
    1.70
    4
    1.69
    3
    1.69
    5
    1.59
    所有
    1.55
    Activations Density 0.042%

    No Known Activations