© 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. 103219
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

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

    The neuron is primarily triggered by numeric tokens (digits and decimal points) such as case numbers, dates, version numbers, and other numeric sequences.

    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
    ouch
    -0.86
    deos
    -0.82
    extend
    -0.80
    党的
    -0.80
    că
    -0.79
     rộng
    -0.76
     quelli
    -0.76
    minton
    -0.75
    ایا
    -0.75
    ált
    -0.75
    POSITIVE LOGITS
    同盟
    0.79
    ートン
    0.73
     Google
    0.71
     as
    0.70
     bc
    0.69
    怪
    0.69
    Arnold
    0.68
     famosas
    0.68
    Prescription
    0.68
     because
    0.67
    Activations Density 0.021%

    No Known Activations