© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48505
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by verbs

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

    This neuron strongly responds to modal and auxiliary verb tokens—especially future‐ and obligation‐marking forms like “will,” “should,” “don’t,” “they’ll,” 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
    $
    -2.33
    '
    -2.23
    </i>
    -2.17
    Bigr
    -1.98
    های
    -1.90
     gravit
    -1.89
    (
    -1.87
    ⦊
    -1.84
    雳
    -1.84
    bigr
    -1.84
    POSITIVE LOGITS
     zahlreichen
    1.94
    厹
    1.80
    氿
    1.70
    ただし
    1.70
    REMARKS
    1.68
     próprios
    1.65
    もしっかり
    1.65
    pantalon
    1.65
     wundersch
    1.63
     %,
    1.61
    Activations Density 0.082%

    No Known Activations