© 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. 22095
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by verbs

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

    The neuron detects modal auxiliary verbs that express obligation or permission (e.g. “must,” “may,” etc.).

    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
    来週
    -1.43
    が無い
    -1.37
    蟥
    -1.36
    Når
    -1.35
    ほら
    -1.34
    あぁ
    -1.34
     配件
    -1.33
     decidi
    -1.30
     putri
    -1.29
    descri
    -1.28
    POSITIVE LOGITS
     to
    1.93
     at
    1.68
     on
    1.52
     was
    1.48
     of
    1.45
    ,
    1.35
     into
    1.33
    4
    1.33
    8
    1.30
     from
    1.30
    Activations Density 0.002%

    No Known Activations