© 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. 27595
    Prev
    Next
    INDEX
    Explanations

    multiplicative formulas and equations

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

    The neuron selectively activates on numeric tokens (including integers, decimals, and hexadecimal 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_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
    烈的
    -0.92
    しかったです
    -0.82
    ležit
    -0.75
     ролях
    -0.75
    cest
    -0.74
    слей
    -0.72
     sia
    -0.70
     Cushion
    -0.70
    vej
    -0.69
     Millet
    -0.69
    POSITIVE LOGITS
     preservation
    0.87
    calidad
    0.84
    preserved
    0.84
    producción
    0.84
     нього
    0.80
    đồ
    0.80
    ttet
    0.80
    спасибо
    0.80
    믈
    0.79
     Preservation
    0.79
    Activations Density 0.056%

    No Known Activations