© 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. 22-GEMMASCOPE-RES-131K
    4. 79858
    Prev
    Next
    INDEX
    Explanations

    fetching data or performing actions

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

    The neuron flags code tokens naming action‐oriented functions or methods (e.g. fetch, get, observe, mount, connect) that initiate data or lifecycle operations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    kea
    -1.07
    voce
    -0.91
     warme
    -0.89
     positifs
    -0.89
    isesti
    -0.89
     branco
    -0.88
    kde
    -0.87
    合って
    -0.86
     มี
    -0.85
    tplatz
    -0.85
    POSITIVE LOGITS
     from
    1.13
     then
    1.05
     картина
    0.93
     just
    0.90
     all
    0.90
    ांक
    0.88
     every
    0.88
    guiar
    0.87
     by
    0.86
    のお話
    0.84
    Activations Density 0.008%

    No Known Activations