© 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. 13688
    Prev
    Next
    INDEX
    Explanations

    image link, how to, file names, system IDs

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

    The neuron is keyed to programming identifier tokens (e.g. variable, field, and alias 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_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
     by
    -3.39
    :
    -2.33
     is
    -2.02
     in
    -1.88
     through
    -1.76
     at
    -1.73
     as
    -1.59
     has
    -1.58
     via
    -1.54
     had
    -1.53
    POSITIVE LOGITS
    鶺
    1.76
     salonu
    1.66
     régal
    1.60
     récol
    1.59
    鹟
    1.58
    鱨
    1.55
    Dí
    1.55
     mélanger
    1.55
     ATTORNEY
    1.52
     yelek
    1.51
    Activations Density 0.037%

    No Known Activations