© 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. 2290
    Prev
    Next
    INDEX
    Explanations

    introductions and named entities

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

    The neuron fires on tokens that represent numbers (dates, years, quantities) and formal named‐entity tokens—especially organization or institution names.

    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
    koda
    -0.73
     Хан
    -0.70
     Bellamy
    -0.67
    UNSIGNED
    -0.67
     Delight
    -0.66
     slider
    -0.66
     ACCOUNT
    -0.65
    尕
    -0.64
     Gifford
    -0.64
     account
    -0.63
    POSITIVE LOGITS
     WX
    0.69
    UPI
    0.68
    ítica
    0.67
    uline
    0.66
    Deep
    0.66
    اب
    0.66
    PAI
    0.66
    endete
    0.65
     Chakra
    0.65
     Panchayat
    0.64
    Activations Density 0.060%

    No Known Activations