© 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. 63057
    Prev
    Next
    INDEX
    Explanations

    expressions of possibility

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

    The neuron is strongly triggered by modal and auxiliary verbs expressing possibility, ability, or intent (e.g. could, may, might, will).

    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
    khid
    -0.97
     aforementioned
    -0.96
     líqu
    -0.94
    しますが
    -0.91
     these
    -0.89
    蹶
    -0.88
    げて
    -0.88
    娯
    -0.86
     kurios
    -0.86
     convencional
    -0.85
    POSITIVE LOGITS
     be
    1.77
     likely
    1.16
     need
    0.96
     not
    0.96
    PROGRESS
    0.94
     επίσης
    0.94
     also
    0.92
     endnu
    0.91
    ¬
    0.91
     help
    0.90
    Activations Density 0.012%

    No Known Activations