© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 45672
    Prev
    Next
    INDEX
    Explanations

    variables and symbols

    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_16_width_262k_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
    '
    1.41
    কে
    1.29
    на
    1.05
     to
    1.00
    2
    1.00
    لت
    0.96
    ن
    0.94
    О
    0.91
    νει
    0.88
    '...
    0.87
    POSITIVE LOGITS
    in
    1.37
    u
    1.00
     zwią
    0.95
    mi
    0.90
    ঙ্গিক
    0.83
    S
    0.79
    。",
    0.78
    로부터
    0.78
     wpły
    0.76
    inizi
    0.76
    Activations Density 0.000%

    No Known Activations