© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 194732
    Prev
    Next
    INDEX
    Explanations

    international or foreign places

    np_acts-logits-general · gemini-2.5-flash-lite

    variation and adaptation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Պ
    0.43
    infused
    0.43
     Biotechnology
    0.42
    イル
    0.41
    されました
    0.41
    ディース
    0.41
    ინი
    0.41
    Զ
    0.41
    DUCED
    0.40
     프리
    0.39
    POSITIVE LOGITS
     lợi
    0.54
     aspectos
    0.52
     கேள்
    0.52
     biện
    0.49
     correctamente
    0.49
     aumentando
    0.48
     especialmente
    0.47
     aumentar
    0.46
     вопросы
    0.45
     medida
    0.45
    Activations Density 0.000%

    No Known Activations