© 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. 34-GEMMASCOPE-RES-131K
    7. 32781
    Prev
    Next
    INDEX
    Explanations

    reflective and red light

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

    The neuron fires on numeric tokens (e.g. reference numbers, measurements, and other digit sequences) in technical or scientific 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
    柢
    -0.93
    роме
    -0.81
    грамм
    -0.77
    ぐり
    -0.75
    诩
    -0.75
    ඝ
    -0.75
    лоди
    -0.73
     Schatten
    -0.73
    IAT
    -0.72
    mella
    -0.72
    POSITIVE LOGITS
     reflective
    2.41
     visibility
    1.94
    reflective
    1.93
     reflectors
    1.73
     reflector
    1.71
     Reflective
    1.69
    反射
    1.58
     retro
    1.50
     reflectivity
    1.47
     reflecting
    1.46
    Activations Density 0.013%

    No Known Activations