© 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. 10780
    Prev
    Next
    INDEX
    Explanations

    get or received

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

    This neuron spotlights tokens for the concept of obtaining/receiving (e.g. “get,” “got,” “receive,” “kregen,” “mendapatkan”).

    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
    on
    -3.11
    to
    -2.61
    𓋼
    -2.47
    はコチラ
    -2.22
    鯓
    -2.17
    はこちらから
    -2.17
    these
    -2.11
    g
    -2.11
    also
    -2.08
    臯
    -2.08
    POSITIVE LOGITS
     hebben
    2.09
     ocurrió
    2.05
     zwarte
    1.95
    簠
    1.94
    IANGLES
    1.91
     wiederhol
    1.90
     sağlar
    1.84
    alleros
    1.83
     системой
    1.80
    言った
    1.78
    Activations Density 0.001%

    No Known Activations