© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15251
    Prev
    Next
    INDEX
    Explanations

    foreign nationalities or relationships

    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
    了一些
    -1.44
    Життє
    -1.31
     berbagai
    -1.29
    了许多
    -1.27
     verschiedenen
    -1.27
    有一些
    -1.26
     quando
    -1.24
     famosa
    -1.24
    了些
    -1.23
     später
    -1.20
    POSITIVE LOGITS
     of
    1.37
     fellow
    1.34
     another
    1.21
     اخیر
    1.20
     equally
    1.19
     rağmen
    1.17
     a
    1.16
     on
    1.14
    gridad
    1.13
     επίσης
    1.12
    Activations Density 0.137%

    No Known Activations