© 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. 22-GEMMASCOPE-RES-131K
    7. 67102
    Prev
    Next
    INDEX
    Explanations

    proglottids, edu, nation

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

    The neuron fires on numeric tokens and quantitative information (counts, statistics, measurements) 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_22/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
    onien
    -0.85
    tilizers
    -0.75
    babwe
    -0.75
    TintMode
    -0.74
    ítja
    -0.74
     Diff
    -0.73
    ABB
    -0.71
    scsi
    -0.69
    那种
    -0.69
    每一个
    -0.69
    POSITIVE LOGITS
     our
    1.27
    ("")
    0.92
    ตัวเอง
    0.92
     coreana
    0.90
     Landkreis
    0.89
     its
    0.87
     réessayer
    0.87
    ApplicationTests
    0.84
    rededor
    0.83
    IBOutlet
    0.81
    Activations Density 0.192%

    No Known Activations