© 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. 60358
    Prev
    Next
    INDEX
    Explanations

    numbers following "posted"

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

    This neuron strongly activates on punctuation tokens, especially quotes (apostrophes and quotation marks) and comment delimiters (e.g. */).

    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
    Kreis
    -0.72
    Axes
    -0.68
    uté
    -0.66
    ＾
    -0.66
     add
    -0.65
     Kreis
    -0.65
    Migration
    -0.63
     Badge
    -0.63
     Depreciation
    -0.63
     Blok
    -0.61
    POSITIVE LOGITS
     LIND
    0.75
     Goblin
    0.73
    ちら
    0.71
    apult
    0.68
    Christianity
    0.67
    estones
    0.67
    Frans
    0.66
    स्था
    0.66
    arek
    0.66
    ึก
    0.66
    Activations Density 0.133%

    No Known Activations