© 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. 25889
    Prev
    Next
    INDEX
    Explanations

    multilingual choices and preferences

    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
     of
    -1.11
     to
    -1.05
     on
    -1.05
    ləş
    -0.94
    fich
    -0.89
    sividad
    -0.87
     pirm
    -0.85
     gibi
    -0.85
    =”
    -0.85
     mutlu
    -0.84
    POSITIVE LOGITS
     equipamento
    1.23
     Choisissez
    1.19
    でしたか
    1.16
     preferencias
    1.16
     kyllä
    1.16
     Utilisez
    1.14
     accesorio
    1.12
     Préférences
    1.10
     различни
    1.10
     Ajoutez
    1.07
    Activations Density 0.021%

    No Known Activations