© 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. 22-GEMMASCOPE-RES-131K
    7. 104643
    Prev
    Next
    INDEX
    Explanations

    scoring, roles, meta, correctly

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

    The neuron activates on numeric tokens (digits and numbers) in the text.

    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
     како
    -0.97
     porosity
    -0.90
     limão
    -0.88
     беше
    -0.88
     MILLER
    -0.87
    harusnya
    -0.85
     humaine
    -0.85
    更加
    -0.84
     termé
    -0.83
     rapides
    -0.83
    POSITIVE LOGITS
    Bety
    1.01
    ikkert
    0.97
     oes
    0.94
    Mvh
    0.87
    ekš
    0.87
     bepaalde
    0.87
    Slik
    0.85
     Ã
    0.85
    soporte
    0.84
     必要
    0.84
    Activations Density 0.131%

    No Known Activations