© 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. 29076
    Prev
    Next
    INDEX
    Explanations

    Department of

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

    The neuron detects the presence of Thai‐language script (i.e. Thai characters or 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
     любых
    -1.59
     Belajar
    -1.56
     ony
    -1.48
    푠
    -1.48
    쾰
    -1.48
     intermin
    -1.46
     любом
    -1.45
     Indem
    -1.44
     ん
    -1.42
     constitue
    -1.42
    POSITIVE LOGITS
     which
    2.42
     and
    1.97
     We
    1.94
     (
    1.86
     of
    1.84
     who
    1.84
     say
    1.79
     for
    1.75
     know
    1.67
     have
    1.66
    Activations Density 0.001%

    No Known Activations