© 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. 10-GEMMASCOPE-RES-131K
    4. 72956
    Prev
    Next
    INDEX
    Explanations

    squash

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

    The neuron consistently activates on occurrences of the substring "squash" (in any context—food, sport, code, or verb).

    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
     This
    -2.19
    ൅
    -2.14
    '
    -2.03
    ёз
    -1.92
    遄
    -1.90
    푉
    -1.89
    ise
    -1.88
    瞜
    -1.86
     cintur
    -1.84
     slated
    -1.83
    POSITIVE LOGITS
    时间的
    2.02
    e
    1.95
    也就是说
    1.94
    这样的
    1.91
    町の
    1.88
    ámicas
    1.80
    are
    1.79
     normalerweise
    1.78
    olybden
    1.77
     острова
    1.77
    Activations Density 0.001%

    No Known Activations