© 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. 10-GEMMASCOPE-RES-131K
    7. 103467
    Prev
    Next
    INDEX
    Explanations

    specialized product compositions

    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
    Neden
    -1.35
     semelhantes
    -1.23
     advierte
    -1.19
    っていますが
    -1.15
    Bericht
    -1.14
    ကိုးကား
    -1.13
    waits
    -1.13
    Selanjutnya
    -1.13
     ję
    -1.13
    ighed
    -1.10
    POSITIVE LOGITS
     both
    1.64
     you
    1.53
     our
    1.43
     your
    1.34
     each
    1.24
     that
    1.23
     now
    1.20
     теперь
    1.20
     either
    1.20
     as
    1.19
    Activations Density 0.127%

    No Known Activations