© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1637
    Prev
    Next
    INDEX
    Explanations

    ### Description

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

    The neuron selectively activates on Chinese (CJK) text segments, especially Chinese headings or labels.

    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
    <h2>
    -1.55
     }}{\
    -0.82
    Yap
    -0.79
    ucher
    -0.73
    ूह
    -0.73
     Jubilee
    -0.69
    ){\
    -0.68
     Primeiro
    -0.68
     ilustracji
    -0.66
    Trichloroethane
    -0.66
    POSITIVE LOGITS
    </h3>
    2.45
    <h3>
    2.03
    </h4>
    1.98
    </h5>
    1.62
    </u>
    1.52
    ",
    
    1.24
     */
    
    1.16
     */
    1.15
    </th>
    1.14
    ,”
    1.10
    Activations Density 0.009%

    No Known Activations