© 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. 39181
    Prev
    Next
    INDEX
    Explanations

    competition results in games or rounds

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

    The neuron activates on numeric tokens—counts, scores, years, and other numbers.

    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
     generando
    -1.45
     provocando
    -1.33
    änomen
    -1.30
     cantando
    -1.27
    ↵↵
    -1.24
     utwor
    -1.19
     creando
    -1.19
     tions
    -1.17
     praticamente
    -1.17
     però
    -1.16
    POSITIVE LOGITS
     aérienne
    1.35
     Giving
    1.32
     Going
    1.31
     гораздо
    1.23
     indien
    1.20
    نر
    1.19
    Going
    1.17
    usammen
    1.17
    新华
    1.17
     級
    1.16
    Activations Density 0.009%

    No Known Activations