© 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. 65042
    Prev
    Next
    INDEX
    Explanations

    US senators

    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
     ویتامین
    -1.36
     more
    -1.36
     its
    -1.21
    ׇ
    -1.16
     indywidual
    -1.13
     their
    -1.13
    Further
    -1.09
    !
    -1.09
     także
    -1.06
     buah
    -1.05
    POSITIVE LOGITS
    ִּ
    1.27
    ύ
    1.27
    Menurutnya
    1.23
    uyasha
    1.15
    ּוֹ
    1.14
     оружи
    1.13
    likte
    1.11
     opponent
    1.11
     موبایل
    1.10
    гія
    1.09
    Activations Density 0.038%

    No Known Activations