© 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. 66018
    Prev
    Next
    INDEX
    Explanations

    code comments and configuration

    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
    我們的
    -1.35
    không
    -1.34
     norvég
    -1.26
    ᅠ
    -1.25
     protège
    -1.25
     chère
    -1.25
     bricolaje
    -1.24
     mojej
    -1.23
     biela
    -1.23
    تمر
    -1.23
    POSITIVE LOGITS
     to
    1.30
     is
    1.17
    so
    1.16
     de
    1.14
    g
    1.13
     C
    1.11
    s
    1.11
    am
    1.09
    co
    1.09
    con
    1.09
    Activations Density 0.003%

    No Known Activations