© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39616
    Prev
    Next
    INDEX
    Explanations

    hustle bustle

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

    The neuron fires on hyphenated reduplicative compound words (e.g. tic-tac-toe, criss-cross, flip-flop, tip-toe).

    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
     and
    -2.09
    ↵
    -1.94
     podczas
    -1.85
     is
    -1.83
     nawet
    -1.73
    诟
    -1.73
     you
    -1.68
    even
    -1.66
     kiedy
    -1.66
    EST
    -1.62
    POSITIVE LOGITS
    zień
    1.94
     stessi
    1.92
    quíni
    1.85
    ńst
    1.81
    ,“
    1.65
     ジップ
    1.65
    minos
    1.63
    liegenden
    1.60
     ويكيميديا
    1.59
    늬
    1.57
    Activations Density 0.021%

    No Known Activations