© 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. 107870
    Prev
    Next
    INDEX
    Explanations

    ) may

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

    The neuron fires on occurrences of the modal “may” (and its immediate context) in formal permission or policy 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
    ownika
    -0.92
     continual
    -0.90
    回头
    -0.84
     perpet
    -0.82
     perpetually
    -0.82
     tenacious
    -0.80
     through
    -0.79
     extenso
    -0.79
     شوید
    -0.79
     gonz
    -0.79
    POSITIVE LOGITS
     answer
    1.09
     jawaban
    0.88
    latable
    0.84
    SubType
    0.81
    transQ
    0.80
     numéro
    0.79
    Asked
    0.79
     answered
    0.79
    Asking
    0.79
     correcta
    0.78
    Activations Density 0.001%

    No Known Activations