© 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. 107804
    Prev
    Next
    INDEX
    Explanations

    search data

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

    The neuron chiefly detects the token “search” (in any context or casing).

    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
     Mackay
    -0.81
    nemonic
    -0.81
    λλά
    -0.79
    alisasi
    -0.79
     museos
    -0.76
    幸运
    -0.75
    ográficas
    -0.74
    是否存在
    -0.73
     minde
    -0.71
    cnpj
    -0.71
    POSITIVE LOGITS
     vorgestellt
    0.87
     cultuur
    0.84
    box
    0.82
     WITHIN
    0.81
     results
    0.81
    ruma
    0.81
    zcze
    0.79
    DataRow
    0.79
    dentro
    0.79
     histórica
    0.78
    Activations Density 0.022%

    No Known Activations