© 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. 39636
    Prev
    Next
    INDEX
    Explanations

    scholar and academic roles

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

    The neuron fires on occurrences of the word “scholar” (including its plural form).

    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
     คือ
    -2.81
     ส์
    -2.73
    
    -2.56
    ญี่ป
    -2.53
    咵
    -2.44
    轳
    -2.44
    柘
    -2.38
    ENSIONS
    -2.36
     aumenta
    -2.34
    Ꞓ
    -2.34
    POSITIVE LOGITS
    0
    4.31
    $
    3.61
    C
    3.55
    [
    3.30
    er
    3.23
    </td>
    3.06
    st
    3.06
    鏵
    3.02
    5
    2.95
    (
    2.92
    Activations Density 0.006%

    No Known Activations