© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45710
    Prev
    Next
    INDEX
    Explanations

    ECM, graphql, Ska

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

    This neuron fires on names of software technologies, libraries, languages, and frameworks (e.g. ECMAScript, GraphQL, ska, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    '
    -3.53
    咈
    -3.44
     Messung
    -3.13
     erase
    -3.06
    ים
    -2.70
    釹
    -2.64
     ก็
    -2.61
    𝄆
    -2.56
    歘
    -2.56
     entonces
    -2.55
    POSITIVE LOGITS
    
    3.53
    鉿
    3.50
    雰
    3.31
    趼
    3.28
    鐿
    3.27
    ዣ
    3.25
    砹
    3.20
    是非常
    3.19
    ⽼
    3.17
    ейчас
    3.14
    Activations Density 0.014%

    No Known Activations