© 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. 10-GEMMASCOPE-RES-131K
    7. 11066
    Prev
    Next
    INDEX
    Explanations

    Midlands, macOS, KFC, Kop

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

    The neuron fires on mid‐sentence capitalized tokens that are true proper nouns—e.g. brand, product, place, or person names—rather than merely sentence‐initial words.

    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
    \
    -4.19
    (
    -3.47
    {
    -3.23
    B
    -2.75
    S
    -2.42
     hålla
    -2.39
     börja
    -2.39
    絃
    -2.36
    ).
    -2.28
    但我
    -2.28
    POSITIVE LOGITS
    0
    2.94
    蒹
    2.78
    殽
    2.70
     avaient
    2.61
    ’
    2.56
     Houſe
    2.56
    ሷ
    2.53
    趼
    2.50
    鲠
    2.50
    퐼
    2.48
    Activations Density 0.012%

    No Known Activations