© 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. 22-GEMMASCOPE-RES-131K
    7. 84051
    Prev
    Next
    INDEX
    Explanations

    certificate, passport, visa

    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_22/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
     we
    -1.70
     our
    -1.55
     often
    -1.42
     $
    -1.34
     his
    -1.32
     Theologie
    -1.28
     \
    -1.27
    ?
    -1.21
     my
    -1.21
     кнопки
    -1.20
    POSITIVE LOGITS
    ּוֹ
    1.75
    辦法
    1.43
    λλη
    1.42
     detalló
    1.41
     MATHEMAT
    1.38
    他們的
    1.35
    BeforeAll
    1.35
     délicieux
    1.34
    轰隆
    1.34
     kraju
    1.34
    Activations Density 0.012%

    No Known Activations