© 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. 40667
    Prev
    Next
    INDEX
    Explanations

    verbs asking questions or describing actions

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

    The neuron fires on formal, “academic‐style” content words—especially longer, less common verbs used in technical or scholarly writing.

    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
     it
    -2.52
     there
    -1.99
     in
    -1.63
     There
    -1.59
    There
    -1.51
    。
    -1.46
     fritas
    -1.46
    What
    -1.40
     on
    -1.34
    there
    -1.31
    POSITIVE LOGITS
     刺繍
    1.41
     čty
    1.38
     všech
    1.33
     největ
    1.30
    zmm
    1.27
     tamamen
    1.25
     dvě
    1.25
     veřej
    1.24
     vijf
    1.23
     tři
    1.22
    Activations Density 0.137%

    No Known Activations