© 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. 99467
    Prev
    Next
    INDEX
    Explanations

    Western Sahara

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

    multiple languages

    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
    ма
    0.56
    дие
    0.49
    t
    0.48
    дата
    0.46
    мя
    0.45
    мы
    0.45
    тивной
    0.45
    the
    0.45
    дам
    0.44
    یات
    0.44
    POSITIVE LOGITS
     봅시다
    0.47
     getMax
    0.46
     negras
    0.44
     removeItem
    0.44
     올
    0.44
     malattie
    0.44
     endGame
    0.44
     peta
    0.43
    輾
    0.43
     ανε
    0.43
    Activations Density 0.000%

    No Known Activations