© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58954
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

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

    The neuron is tuned to spot numeric tokens—digits, decimal points, and related punctuation in numbers.

    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
     Shel
    -0.80
     yar
    -0.75
     mauvais
    -0.74
    applicant
    -0.74
     Logger
    -0.74
    รัก
    -0.74
     Tisch
    -0.73
     að
    -0.72
     petit
    -0.71
     BorderRadius
    -0.71
    POSITIVE LOGITS
     IGN
    0.85
     witcher
    0.82
    挝
    0.80
    ⅔
    0.79
     xenon
    0.79
    ಕ್ಕ
    0.78
     subver
    0.77
    bura
    0.75
     Bubba
    0.75
    tivo
    0.73
    Activations Density 0.042%

    No Known Activations