© 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. 8780
    Prev
    Next
    INDEX
    Explanations

    xml, code, filenames

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

    The neuron is highly responsive to punctuation and delimiter tokens (commas, parentheses, brackets), standalone numerals, and other non-standard script tokens.

    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
     penerbangan
    -1.77
     Üniversitesi
    -1.66
    Мі
    -1.65
     свою
    -1.64
     उपकरण
    -1.59
    τας
    -1.55
     vry
    -1.53
     havet
    -1.52
     debilitating
    -1.50
    FRANC
    -1.49
    POSITIVE LOGITS
     are
    1.84
     [
    1.80
     (
    1.80
     {
    1.73
     Kindheit
    1.73
    .
    1.72
     ogóle
    1.61
     gewöhnlich
    1.60
     charakterysty
    1.59
    屄
    1.59
    Activations Density 0.001%

    No Known Activations