© 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. 115460
    Prev
    Next
    INDEX
    Explanations

    OpenLayers App LICENSE cvs show

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

    The neuron fires on code‐style tokens—things like programming identifiers, version numbers, and other uppercase or alphanumeric elements in code snippets.

    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
     Literature
    -0.68
    Preston
    -0.67
    bori
    -0.66
     Makoto
    -0.65
     köz
    -0.64
    aspir
    -0.64
    lexer
    -0.64
     aank
    -0.63
     sł
    -0.61
     Departure
    -0.61
    POSITIVE LOGITS
     صند
    0.81
     बैठ
    0.73
     dépens
    0.72
     范
    0.69
    經典
    0.69
     Wallet
    0.68
    噠
    0.66
    サス
    0.64
     ランキング
    0.64
    وزش
    0.64
    Activations Density 0.045%

    No Known Activations