© 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. 34-GEMMASCOPE-RES-131K
    7. 93341
    Prev
    Next
    INDEX
    Explanations

    Ralph Hungerford Kengo Ota Azure

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

    The neuron detects spans of Japanese‐language text (Japanese characters and 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_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
    aní
    -0.83
     berkunjung
    -0.82
    ücksich
    -0.82
    joo
    -0.79
    lenie
    -0.77
    Título
    -0.75
    siębior
    -0.75
    neighbour
    -0.74
    otho
    -0.73
     Illuminated
    -0.73
    POSITIVE LOGITS
    [!
    1.26
     :::
    0.91
    :::
    0.88
    ⅖
    0.79
     Azure
    0.77
     scher
    0.74
     Szen
    0.73
    seal
    0.73
    . 
    0.72
    DDL
    0.71
    Activations Density 0.050%

    No Known Activations