© 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. 10-GEMMASCOPE-RES-131K
    7. 86162
    Prev
    Next
    INDEX
    Explanations

    UV, insecticide, chip, storage, barcode, nano, motor, bacteria, uint

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

    technical or product-specific information with measurements, specifications, and technical terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires most strongly on salient, domain‐specific content words (technical or topic keywords) rather than on common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    m
    -2.78
    k
    -2.70
    il
    -2.53
     
    -2.53
    on
    -2.44
    en
    -2.44
    h
    -2.41
    is
    -2.41
    l
    -2.39
    u
    -2.33
    POSITIVE LOGITS
    ubahan
    2.28
     帳
    2.05
    wachen
    2.02
    官網
    1.98
    imbangan
    1.95
     設置
    1.91
    aruhi
    1.90
    Bahasa
    1.88
    libat
    1.87
    jelasan
    1.86
    Activations Density 43.762%

    No Known Activations