© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124756
    Prev
    Next
    INDEX
    Explanations

    feel overwhelmed

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    a
    -1.92
    '
    -1.86
     to
    -1.74
     装着
    -1.73
     lho
    -1.66
     لين
    -1.64
     ì
    -1.63
    o
    -1.58
    on
    -1.55
     ウール
    -1.53
    POSITIVE LOGITS
     amikor
    1.63
     bañ
    1.61
    endsection
    1.59
    Thêm
    1.47
     casas
    1.47
    mybatisplus
    1.45
     slender
    1.43
    llten
    1.43
    anjutan
    1.43
     llam
    1.42
    Activations Density 0.021%

    No Known Activations