© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11890
    Prev
    Next
    INDEX
    Explanations

    Southern Poverty Law Center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     southwest
    0.54
     south
    0.51
     Southwest
    0.50
     South
    0.50
    west
    0.47
    south
    0.45
     साउथ
    0.44
    南
    0.44
     west
    0.44
     southeast
    0.43
    POSITIVE LOGITS
    most
    0.55
     Hemisphere
    0.46
    MOST
    0.42
     hemisphere
    0.40
     लाइट्स
    0.40
     puisqu
    0.39
    efois
    0.39
    зіно
    0.38
    IZATION
    0.37
    ுகிற
    0.37
    Activations Density 0.027%

    No Known Activations