© 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. 86637
    Prev
    Next
    INDEX
    Explanations

    page citations

    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
     with
    -1.51
    さまざま
    -1.36
     âgé
    -1.30
    の中には
    -1.27
    どういう
    -1.25
    と思った
    -1.23
    Udo
    -1.18
    欒
    -1.17
    young
    -1.16
     biraz
    -1.16
    POSITIVE LOGITS
     it
    1.58
    :
    1.53
    中部
    1.39
    tonsoft
    1.30
    دکتر
    1.30
    眼下
    1.29
    　　“
    1.28
     and
    1.28
    redmi
    1.28
    مقال
    1.27
    Activations Density 0.027%

    No Known Activations