© 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. 10-GEMMASCOPE-RES-131K
    7. 124166
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

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

    This neuron fires on numeric literals and related math-notation tokens (e.g. numbers, decimal points, exponent (“**”) operators) in 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_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
     และ
    -1.59
     dopo
    -1.49
    titure
    -1.46
     apenas
    -1.44
     après
    -1.40
    atility
    -1.37
    𓁹
    -1.35
     após
    -1.31
     ו
    -1.29
     très
    -1.29
    POSITIVE LOGITS
     Those
    1.41
     deceitful
    1.37
     ingrained
    1.16
    烩
    1.14
    Those
    1.10
     tenacious
    1.09
     Mereka
    1.09
     Obviously
    1.09
     började
    1.08
     ingenious
    1.06
    Activations Density 0.056%

    No Known Activations