© 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. 34676
    Prev
    Next
    INDEX
    Explanations

    on Windows

    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
     your
    -1.80
     or
    -1.45
     either
    -1.18
     eneste
    -1.00
     ONLY
    -0.97
     paliwa
    -0.95
     odası
    -0.94
     hvorfor
    -0.94
     any
    -0.93
     as
    -0.93
    POSITIVE LOGITS
    Моя
    1.10
     but
    1.06
    お知らせ
    1.05
     ellas
    1.04
    ButtonPressed
    1.02
     my
    1.02
    Disclaimer
    0.96
    Друзья
    0.95
     becauſe
    0.95
    because
    0.94
    Activations Density 0.035%

    No Known Activations