© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68178
    Prev
    Next
    INDEX
    Explanations

    adverbs of manner or circumstance

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

    The neuron fires on words that signal quantitative or measurement contexts—e.g. adverbs and adjectives used to express degrees, amounts, rates, or variability.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     in
    -1.46
     here
    -1.26
     στο
    -1.17
    ใน
    -1.13
     здесь
    -1.13
     across
    -1.10
    在这
    -1.08
    在
    -1.08
     ở
    -0.98
     outdoors
    -0.98
    POSITIVE LOGITS
    باح
    1.11
     largas
    0.98
     Jungfrau
    0.95
    ungal
    0.90
     after
    0.89
    ๋า
    0.88
    threading
    0.87
    ımız
    0.86
    posizione
    0.85
    িয়ে
    0.84
    Activations Density 0.092%

    No Known Activations