© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13126
    Prev
    Next
    INDEX
    Explanations

    search, investigación, buscar

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

    The neuron detects words meaning “search” or “look for” (e.g. search, buscar, busca, look for, иск) across different languages.

    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
    泐
    -2.16
    ଼
    -2.13
    媃
    -2.02
     轉
    -1.93
    镦
    -1.91
    ulieren
    -1.91
    ;}
    -1.90
    にゃ
    -1.89
    ご注意
    -1.88
    鸯
    -1.87
    POSITIVE LOGITS
    in
    3.19
    an
    2.61
    or
    2.31
    a
    2.25
    ar
    2.23
    ther
    2.17
     in
    2.17
    at
    2.08
    ↵↵
    2.06
     it
    1.98
    Activations Density 0.023%

    No Known Activations