© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47574
    Prev
    Next
    INDEX
    Explanations

    quantities and sizes

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

    The neuron activates on quantitative magnitude descriptors—adjectives and adverbs that indicate relative size or amount (e.g. small, large, several, thousands, short, multiple).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ांकि
    -1.42
     Также
    -1.35
     camiones
    -1.32
     recomendado
    -1.31
    那个人
    -1.30
    ล้ว
    -1.30
    Karakteristik
    -1.29
     about
    -1.27
     gimnasio
    -1.26
     ftate
    -1.26
    POSITIVE LOGITS
     as
    1.75
     как
    1.57
     of
    1.38
    !
    1.30
    му
    1.23
     comme
    1.15
    дер
    1.14
     tinggi
    1.14
    Как
    1.13
    сами
    1.13
    Activations Density 0.245%

    No Known Activations