© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26041
    Prev
    Next
    INDEX
    Explanations

    references bibliography external links

    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
     will
    -1.31
    توضیحات
    -1.27
     in
    -1.24
    nextLine
    -1.09
    خبر
    -1.05
    پاسخ
    -1.04
     while
    -1.03
    onResume
    -1.03
     மற்றும்
    -1.02
     which
    -1.01
    POSITIVE LOGITS
     trouver
    1.27
     utiliser
    1.26
     pfle
    1.16
    Hôtel
    1.16
     dianteiro
    1.09
     aſ
    1.09
    ストール
    1.05
     ſi
    1.05
    pecu
    1.04
     ersche
    1.03
    Activations Density 0.003%

    No Known Activations