© 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. 86956
    Prev
    Next
    INDEX
    Explanations

    areas of expertise and accomplishment

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

    The neuron fires on very common, high‐frequency tokens (e.g. “’s,” “biggest,” “career,” “professional,” “the,” “in,” “a,” etc.).

    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
    zną
    -0.85
    Emissions
    -0.83
     Willen
    -0.76
     surgeons
    -0.75
    シェフ
    -0.75
     electrodes
    -0.74
    ゴミ
    -0.72
    ！）
    -0.71
    Surgery
    -0.71
    chule
    -0.71
    POSITIVE LOGITS
     culinary
    2.17
     crick
    1.81
     aviation
    1.72
     automotive
    1.70
     musical
    1.70
     golfing
    1.69
     gaming
    1.68
     horticultural
    1.63
     gardening
    1.60
     literary
    1.58
    Activations Density 0.340%

    No Known Activations