© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13728
    Prev
    Next
    INDEX
    Explanations

    while [doing something]

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

    The neuron fires on present‐participial (–ing) verbs used to introduce time‐setting subordinate clauses (e.g. “While working…,” “While investigating…,” “Looking through…”).

    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
    ありますが
    -1.61
     begy
    -1.52
     sintética
    -1.51
     what
    -1.48
     that
    -1.46
     descuentos
    -1.43
     imprimible
    -1.40
     integrados
    -1.35
     aplicado
    -1.35
     bloques
    -1.34
    POSITIVE LOGITS
    alties
    1.59
    ines
    1.58
     on
    1.46
     età
    1.41
    </tfoot>
    1.35
     например
    1.34
     Você
    1.33
     soirée
    1.33
    ској
    1.27
     insbesondere
    1.27
    Activations Density 0.038%

    No Known Activations