© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100188
    Prev
    Next
    INDEX
    Explanations

    verb followed by object

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

    The neuron lights up on semantically “heavy” or high-information words—especially key action verbs and other content words that often serve as the main focus or keywords in a sentence.

    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
     of
    -2.30
     will
    -1.78
     on
    -1.77
     have
    -1.49
     other
    -1.47
     would
    -1.45
     despite
    -1.45
     by
    -1.42
     without
    -1.42
     after
    -1.36
    POSITIVE LOGITS
     bebés
    1.49
     sowohl
    1.45
     deportistas
    1.45
     jste
    1.43
     amables
    1.42
     hogares
    1.41
     manicura
    1.38
    -
    1.38
     oído
    1.38
     hlavně
    1.36
    Activations Density 0.271%

    No Known Activations