© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64680
    Prev
    Next
    INDEX
    Explanations

    racing drivers or questions

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

    This neuron detects numeric tokens—especially multi‐digit numbers (years, counts, and other quantitative data) in the text.

    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
     this
    -0.90
    ynia
    -0.75
     ।
    -0.73
     蒸
    -0.73
     by
    -0.71
    enej
    -0.70
     five
    -0.70
     juni
    -0.69
     Go
    -0.69
     arra
    -0.68
    POSITIVE LOGITS
    nerability
    0.90
     cóc
    0.85
     innych
    0.85
    still
    0.84
    lave
    0.84
    tudi
    0.83
    atiques
    0.82
     autres
    0.82
    örande
    0.82
     スポット
    0.82
    Activations Density 0.008%

    No Known Activations