© 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. 73826
    Prev
    Next
    INDEX
    Explanations

    introductions and statements of fact

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

    The neuron detects Japanese-language tokens (hiragana/kanji).

    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
    僭
    -2.34
    
    -2.33
     flurry
    -2.33
    曩
    -2.14
     waarschijnlijk
    -2.14
    哔
    -2.11
    所说的
    -2.06
    驺
    -2.06
    not
    -2.05
     kteří
    -2.05
    POSITIVE LOGITS
    $
    3.00
    </i>
    2.91
    The
    2.89
    0
    2.52
    {
    2.47
    [
    2.47
    媜
    2.42
    Where
    2.33
    なら
    2.25
    (
    2.23
    Activations Density 0.000%

    No Known Activations