© 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. 34-GEMMASCOPE-RES-131K
    7. 78315
    Prev
    Next
    INDEX
    Explanations

    if ... would

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

    The neuron strongly activates on common single‐word pronouns and demonstratives (e.g. “it,” “that,” “I”), i.e. high-frequency function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Will
    -1.71
    will
    -1.52
     gonna
    -1.46
    would
    -1.41
    Would
    -1.41
    是
    -1.38
     Would
    -1.34
     Will
    -1.34
     Gonna
    -1.34
    WILL
    -1.30
    POSITIVE LOGITS
    ὠ
    1.07
     Siglo
    1.02
     ANNE
    0.94
     Rè
    0.94
     Zelanda
    0.93
     Frédéric
    0.92
     Maldonado
    0.89
     CANADIAN
    0.89
     lauk
    0.88
    tigte
    0.86
    Activations Density 0.132%

    No Known Activations