© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3573
    Prev
    Next
    INDEX
    Explanations

    if it

    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_22_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
     których
    0.72
     என்னும்
    0.70
    ను
    0.69
    の
    0.69
     તેમના
    0.68
    さて
    0.68
     denen
    0.67
     auxquels
    0.67
    このような
    0.66
    Thats
    0.66
    POSITIVE LOGITS
     it
    4.57
    It
    3.89
     It
    3.82
    it
    3.18
    它
    3.14
     它
    2.77
    มัน
    2.72
     оно
    2.64
     nó
    2.47
     มัน
    2.40
    Activations Density 4.787%

    No Known Activations