© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68124
    Prev
    Next
    INDEX
    Explanations

    Japanese and English conjunctions

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

    The neuron identifies Japanese-language text fragments (e.g. sequences of kanji, hiragana, or katakana).

    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
    銪
    -1.55
    ↵
    -1.55
    泺
    -1.54
     telefónica
    -1.49
     synonym
    -1.45
    넋
    -1.45
    ꧁
    -1.45
     つけ
    -1.44
    Gira
    -1.42
    Eure
    -1.41
    POSITIVE LOGITS
     to
    2.05
     You
    1.64
     Quando
    1.55
    *
    1.52
     that
    1.36
     Não
    1.33
    Eventually
    1.30
    to
    1.29
    苙
    1.27
     I
    1.25
    Activations Density 0.008%

    No Known Activations