© 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. 22-GEMMASCOPE-RES-131K
    7. 26915
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and expressions

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

    The neuron fires on LaTeX math tokens—especially variable names (like “aₙ” with underscores), function names (like “\ln”), and other math identifiers inside formulas.

    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
     miniaturka
    -1.02
     cadeaux
    -0.98
    Klik
    -0.98
     utilisateur
    -0.97
     controladores
    -0.96
     multiuso
    -0.95
     urat
    -0.94
     estampada
    -0.93
     atleta
    -0.93
     Tentang
    -0.92
    POSITIVE LOGITS
     one
    0.94
     otras
    0.93
     from
    0.92
     and
    0.90
     other
    0.86
     their
    0.85
    越高
    0.83
     while
    0.82
     verfol
    0.80
    rokken
    0.80
    Activations Density 0.045%

    No Known Activations