© 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. 27008
    Prev
    Next
    INDEX
    Explanations

    section numbers {#sec}

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

    The neuron strongly activates on Arabic numeral tokens used for list, section, figure, or episode numbering—that is, it detects numeric labels.

    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
    wut
    -0.91
     iconFacebook
    -0.87
     hoi
    -0.87
    centrum
    -0.86
     技术
    -0.85
     leger
    -0.82
    crania
    -0.81
     same
    -0.81
     אותם
    -0.80
     Perla
    -0.79
    POSITIVE LOGITS
    avantage
    0.89
     boyunca
    0.85
     excites
    0.83
     Übungen
    0.82
    étaires
    0.80
     przygoto
    0.80
     kaplama
    0.79
    ഊ
    0.78
     dreaded
    0.77
    (!__
    0.77
    Activations Density 0.002%

    No Known Activations