© 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. 110492
    Prev
    Next
    INDEX
    Explanations

    organization actions

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

    The neuron flags formal event‐ or action‐describing verbs (e.g. held, holds, presents, publishes, partners, distributes) typically used in institutional announcements.

    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
     terpisah
    -1.50
     keindahan
    -1.45
     ilmiah
    -1.38
    Jeudi
    -1.38
    licante
    -1.36
    新しい
    -1.33
    رأة
    -1.33
    这些
    -1.33
     termurah
    -1.33
    Опис
    -1.30
    POSITIVE LOGITS
     you
    2.03
     of
    1.23
    其余
    1.22
    -
    1.22
    ing
    1.22
    却被
    1.20
    ‌.
    1.20
    tak
    1.16
     Departement
    1.13
     is
    1.13
    Activations Density 0.220%

    No Known Activations