© 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. 22-GEMMASCOPE-RES-131K
    7. 34489
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by verbs or nouns

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

    This neuron detects modal or auxiliary verbs and related function words that express possibility/necessity (e.g. “may,” “have,” “to”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    mby
    -1.61
     efektif
    -1.52
     komer
    -1.52
    certainly
    -1.49
    raeli
    -1.48
     kekinian
    -1.48
    ebly
    -1.45
     sudadera
    -1.44
     indik
    -1.43
    rophi
    -1.42
    POSITIVE LOGITS
    L
    1.72
    N
    1.70
    J
    1.68
    F
    1.63
    M
    1.62
    T
    1.57
    B
    1.56
    S
    1.56
    C
    1.55
    A
    1.52
    Activations Density 0.085%

    No Known Activations