© 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. 111060
    Prev
    Next
    INDEX
    Explanations

    giving or putting something

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

    The neuron fires on verbs (and their inflections) that describe the act of contributing or delivering sports statistics—especially “give,” “gave,” “giving,” “opened,” “put (on),” etc., when reporting goals, points, saves, or other game events.

    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
     a
    -1.99
     spesso
    -1.51
     +(
    -1.45
    ↵
    -1.36
     $+$
    -1.36
     stále
    -1.31
     \_
    -1.27
     opět
    -1.27
     🔥
    -1.27
    不是
    -1.27
    POSITIVE LOGITS
    Ꮸ
    1.68
    荩
    1.67
    分ほど
    1.44
    viä
    1.41
    ض
    1.39
     proceeding
    1.37
    Let
    1.36
    よろ
    1.35
     cias
    1.33
    Perhaps
    1.30
    Activations Density 0.011%

    No Known Activations