© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63709
    Prev
    Next
    INDEX
    Explanations

    code comments and keywords

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

    The neuron specializes in spotting standalone numeric tokens (numeric literals or version numbers) 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
    肩膀
    -0.75
    klo
    -0.73
     واح
    -0.72
     تهد
    -0.71
    向下
    -0.70
     doorstep
    -0.69
    ראה
    -0.68
     Corbin
    -0.68
    stringValue
    -0.66
    بعاد
    -0.66
    POSITIVE LOGITS
    卉
    0.78
    楼主
    0.71
     完全
    0.69
    ți
    0.68
    quilibrium
    0.67
    GORITHM
    0.65
    梅花
    0.65
    iting
    0.64
    њу
    0.64
    acci
    0.63
    Activations Density 0.038%

    No Known Activations