© 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. 160920
    Prev
    Next
    INDEX
    Explanations

    specific contextual details

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

    different versions/types

    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
     일반적으로
    0.46
     혹은
    0.46
     добра
    0.44
     ולא
    0.44
     및
    0.43
     를
    0.43
     또는
    0.43
     вас
    0.43
     왜
    0.43
     달라
    0.41
    POSITIVE LOGITS
    disease
    0.46
    金属
    0.44
     Nahrung
    0.44
     Consulting
    0.43
     Rezept
    0.42
     proteolytic
    0.41
    বিধি
    0.41
     Disease
    0.41
     Formatting
    0.41
     erythro
    0.40
    Activations Density 0.000%

    No Known Activations