© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117527
    Prev
    Next
    INDEX
    Explanations

    formula and its context

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

    The neuron identifies the word "Formula" and its variants (including "Fórmula"), particularly when it appears at the beginning of a text segment or as part of a technical or mathematical context.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     professora
    -1.06
     formes
    -1.03
    Harley
    -1.03
    浿
    -1.03
     voedsel
    -1.00
    溷
    -1.00
     unimaginable
    -0.99
    柔ら
    -0.99
    ментом
    -0.98
    
    -0.98
    POSITIVE LOGITS
    formula
    1.73
     formula
    1.65
    Formula
    1.63
     formulae
    1.52
     Formula
    1.48
     formulas
    1.37
    !”
    1.18
    ”
    1.18
     FORMULA
    1.15
     Formulas
    1.12
    Activations Density 0.016%

    No Known Activations