© 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. 130065
    Prev
    Next
    INDEX
    Explanations

    University of Washington

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

    This neuron detects mentions of the University of Washington (including “UW” and its full name).

    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
    他的
    -2.78
    蹀
    -2.34
    鞮
    -2.34
    舠
    -2.28
    mockMvc
    -2.20
     mesmas
    -2.20
     лучший
    -2.19
    ኵ
    -2.16
    各样的
    -2.14
    鏷
    -2.13
    POSITIVE LOGITS
    are
    2.69
     femeninos
    2.38
    as
    2.11
    ଽ
    2.11
    逦
    2.09
    ⤻
    2.09
     esthétique
    2.08
     руке
    2.05
     що
    2.03
     surpren
    2.03
    Activations Density 0.004%

    No Known Activations