© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81770
    Prev
    Next
    INDEX
    Explanations

    UI design and designers

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

    The neuron fires on technical/data tokens—things like URLs (e.g. “://”, domain fragments), code‐style identifiers, and standalone numbers or version markers.

    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
    KommentareTeilen
    -0.77
     کلاس
    -0.75
    Tier
    -0.75
     правительства
    -0.74
    跌
    -0.74
    جين
    -0.72
    ⁂
    -0.71
    ℛ
    -0.71
    ♬
    -0.70
     Méd
    -0.69
    POSITIVE LOGITS
     Dri
    1.63
    dri
    1.45
    Dri
    1.34
     dri
    1.29
     UI
    1.28
     designers
    1.21
     Designers
    1.17
     дизай
    1.08
    UI
    1.05
     design
    1.03
    Activations Density 0.058%

    No Known Activations