© 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. 20840
    Prev
    Next
    INDEX
    Explanations

    modal verbs

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

    The neuron activates on modal and auxiliary verbs (e.g. will, may, must, can, unable) that signal ability, permission, obligation, or future action.

    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
    </strong>
    -1.63
    ”
    -1.53
    u
    -1.48
     Bäume
    -1.43
    -
    -1.38
     our
    -1.38
    ské
    -1.35
    ότη
    -1.35
    ’
    -1.34
    ,"
    -1.30
    POSITIVE LOGITS
    涐
    1.66
     بعد
    1.53
     menggunakan
    1.48
     appunt
    1.46
    ستارهای
    1.45
     俺
    1.44
    rücke
    1.43
     他
    1.42
    なのかな
    1.42
    之后
    1.41
    Activations Density 0.097%

    No Known Activations