© 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. 84490
    Prev
    Next
    INDEX
    Explanations

    Fox News Sunday, Adventures

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

    The neuron is tuned to detect numeric tokens and quantitative expressions (e.g. standalone digits, multi-digit numbers, ages, counts, dates).

    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
     without
    -1.23
     cérami
    -1.12
    comida
    -1.12
     Dijo
    -1.05
    पाद
    -1.05
     coloris
    -1.05
     their
    -1.03
     Tampoco
    -1.02
     cortinas
    -1.02
     mancha
    -0.97
    POSITIVE LOGITS
    arthed
    1.10
     stwor
    1.09
    あぁ
    1.01
     человеку
    1.00
     Americans
    0.98
    ड़ा
    0.97
    我也是
    0.96
    又是一
    0.96
    ACIONES
    0.96
     staff
    0.95
    Activations Density 0.003%

    No Known Activations