© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60722
    Prev
    Next
    INDEX
    Explanations

    foreign requests and names

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

    The neuron fires on polite request or gratitude expressions (e.g. “Прошу,” “Demander,” “Agradeço,” etc.).

    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
    ﾚ
    -2.00
     versões
    -1.97
    }$,
    -1.97
     utilised
    -1.96
     didn
    -1.95
     understand
    -1.85
    　　（
    -1.85
     để
    -1.78
     also
    -1.77
     know
    -1.77
    POSITIVE LOGITS
    韡
    2.34
    勦
    2.28
    翾
    2.16
    かっこ
    2.05
     cliquer
    2.03
     Of
    2.02
    as
    2.02
     réun
    2.00
     kteří
    1.97
     regarder
    1.86
    Activations Density 0.002%

    No Known Activations