© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75820
    Prev
    Next
    INDEX
    Explanations

    front button and zip closure

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

    This neuron activates on words naming garment fasteners (e.g., buttons, zippers, buckles, lacing).

    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
    อบ
    -0.76
    诣
    -0.75
     Gegenteil
    -0.75
    bead
    -0.73
    лиз
    -0.73
     bestätigen
    -0.70
    stina
    -0.68
     Double
    -0.68
     xách
    -0.68
    valdo
    -0.68
    POSITIVE LOGITS
    up
    0.93
    FRONT
    0.89
     up
    0.88
     closure
    0.85
     frontal
    0.81
    Produk
    0.78
     front
    0.77
     Eri
    0.75
     Boot
    0.75
     ?
    0.73
    Activations Density 0.083%

    No Known Activations