© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79193
    Prev
    Next
    INDEX
    Explanations

    may followed by possibility

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

    The neuron activates on occurrences of the modal auxiliary “may,” especially in disclaimer‐style or uncertainty statements.

    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
    踽
    -1.77
    ඞ
    -1.72
    aneity
    -1.67
    rée
    -1.61
    ·
    -1.59
     BERNAMA
    -1.59
    PENUTUP
    -1.52
    ⃢
    -1.49
    薷
    -1.48
    纛
    -1.47
    POSITIVE LOGITS
     be
    4.25
     have
    2.55
     not
    2.50
     also
    2.08
    There
    1.79
    It
    1.71
    What
    1.69
    How
    1.69
     may
    1.67
     être
    1.63
    Activations Density 0.088%

    No Known Activations