© 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. 50121
    Prev
    Next
    INDEX
    Explanations

    eating utensils or cutlery

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

    The neuron strongly activates on occurrences of “spoon” (and its variants/substrings) in the text.

    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
    ジャパン
    -0.77
    y
    -0.73
     Irvine
    -0.71
    Schw
    -0.70
    yaret
    -0.69
    適量
    -0.69
     所
    -0.68
     Nasıl
    -0.67
    igan
    -0.66
    mu
    -0.65
    POSITIVE LOGITS
     spoon
    3.00
     spoons
    2.73
     Spoon
    2.56
    spoon
    2.47
    Spoon
    2.38
    🥄
    2.16
     fork
    1.84
    Fork
    1.67
     Spo
    1.66
     SPO
    1.62
    Activations Density 0.015%

    No Known Activations