© 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. 115704
    Prev
    Next
    INDEX
    Explanations

    passing or failing exams

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

    The neuron strongly activates on numeric tokens (digits and numbers), especially those denoting scores, counts, years, or other quantitative data.

    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
     aufgestellt
    -0.83
    ätter
    -0.83
    letterSpacing
    -0.80
    ablanca
    -0.79
    CUSSION
    -0.77
    ppery
    -0.77
     判断
    -0.75
     smtplib
    -0.73
     avanzar
    -0.72
    BOW
    -0.72
    POSITIVE LOGITS
     exams
    3.75
     exam
    3.25
     examinations
    2.89
     examination
    2.42
    exams
    2.28
     Exams
    2.14
     tests
    2.06
    考试
    2.05
    exam
    2.02
    Exams
    2.00
    Activations Density 0.034%

    No Known Activations