© 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. 22-GEMMASCOPE-RES-131K
    7. 71896
    Prev
    Next
    INDEX
    Explanations

    I hope, Are you joking

    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
     vinil
    -1.33
     ویکی‌پدیا
    -1.24
     which
    -1.23
     ané
    -1.23
     linge
    -1.20
     Censo
    -1.19
     profesion
    -1.12
     asfalto
    -1.11
     bronz
    -1.10
    
    -1.10
    POSITIVE LOGITS
    Hmmm
    1.29
     deudas
    1.16
     gigantic
    1.16
     sanciones
    1.15
     berücksichtigt
    1.13
     Besonder
    1.13
    \
    1.11
    ３
    1.09
    More
    1.09
     l
    1.09
    Activations Density 0.009%

    No Known Activations