© 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. 90742
    Prev
    Next
    INDEX
    Explanations

    mathematical and physical representations

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

    The neuron selectively activates on tokens inside mathematical formulae—especially LaTeX math mode delimiters (`$`) and the symbols, operators, and names within them.

    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
     during
    -0.77
    нитель
    -0.69
     getUsername
    -0.68
    嫔
    -0.66
    Демографія
    -0.66
     ventri
    -0.65
     deleteUser
    -0.64
    romptu
    -0.63
    vernight
    -0.63
     kna
    -0.63
    POSITIVE LOGITS
    CCR
    0.99
     Haag
    0.88
    Carrito
    0.83
    Спо
    0.83
    Energy
    0.82
    States
    0.81
    كي
    0.80
    pias
    0.79
    cripción
    0.79
     Tomaten
    0.79
    Activations Density 0.036%

    No Known Activations