© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12408
    Prev
    Next
    INDEX
    Explanations

    with open as f

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    ي
    0.96
    assertInstanceOf
    0.91
    াইলেন
    0.84
    গন
    0.84
    руются
    0.84
     logic
    0.83
    ாலிக
    0.82
    or
    0.78
    س
    0.78
    ypse
    0.77
    POSITIVE LOGITS
    Conservation
    1.04
     познакоми
    1.03
     дости
    1.03
     суть
    1.03
    completely
    1.01
    [:]
    0.97
     scompar
    0.96
    marque
    0.95
    toadd
    0.94
    Hood
    0.94
    Activations Density 0.002%

    No Known Activations