© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48901
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

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

    The neuron activates on Chinese (CJK) characters 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_34/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
     at
    -1.19
     so
    -1.18
     on
    -1.17
     by
    -1.07
     (
    -1.06
     in
    -1.02
     all
    -0.95
     have
    -0.93
    </h1>
    -0.93
     our
    -0.93
    POSITIVE LOGITS
    に入れる
    1.03
    ಃ
    1.00
    理石
    0.98
    仍然
    0.98
    ρίς
    0.97
     alcuni
    0.96
     evaluaciones
    0.95
     Redacción
    0.94
    íguez
    0.94
     Además
    0.94
    Activations Density 0.001%

    No Known Activations