© 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. 99843
    Prev
    Next
    INDEX
    Explanations

    sales leads

    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
    ↵
    -1.86
     —
    -1.67
    siasme
    -1.52
    4
    -1.45
     kolejny
    -1.43
     {
    -1.43
    3
    -1.43
     שונים
    -1.42
    6
    -1.41
    ed
    -1.41
    POSITIVE LOGITS
    廛
    1.72
    詒
    1.67
     ПОД
    1.55
    钨
    1.52
     ВЫ
    1.52
     ИН
    1.52
     Ін
    1.52
     Профиль
    1.52
     ИЗ
    1.52
    buddha
    1.52
    Activations Density 0.021%

    No Known Activations