© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44982
    Prev
    Next
    INDEX
    Explanations

    previous / current chapter

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

    This neuron responds to Chinese characters (e.g. hanzi) 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_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
     commerciales
    -2.66
     =
    -2.41
     setEmail
    -2.38
    艫
    -2.28
    ar
    -2.28
    ?”
    -2.23
     setLoading
    -2.23
    ႐
    -2.19
    si
    -2.19
     financières
    -2.16
    POSITIVE LOGITS
     It
    3.22
    </em>
    3.13
    ↵
    2.89
    嵛
    2.56
     However
    2.45
                
    2.41
     Meanwhile
    2.30
    <
    2.23
     Wonderful
    2.20
     Things
    2.19
    Activations Density 0.000%

    No Known Activations