© 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. 34-GEMMASCOPE-RES-131K
    7. 107693
    Prev
    Next
    INDEX
    Explanations

    possibility, perhaps, maybe

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

    The neuron primarily detects occurrences of the word “may” (the modal verb).

    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
    arzt
    -0.84
     Autónoma
    -0.83
    øs
    -0.81
     brug
    -0.79
    ersburg
    -0.79
     Symfony
    -0.79
     fusil
    -0.78
    sonder
    -0.78
    манов
    -0.78
    stral
    -0.78
    POSITIVE LOGITS
     perhaps
    1.71
     Perhaps
    1.71
     Possibly
    1.69
    Perhaps
    1.68
     possibly
    1.66
    Possibly
    1.65
    haps
    1.52
    perhaps
    1.50
    possibly
    1.38
     быть
    1.31
    Activations Density 0.032%

    No Known Activations