© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3039
    Prev
    Next
    INDEX
    Explanations

    North America, South America, China regions

    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
    াদি
    0.71
     বাঙালী
    0.71
    넬
    0.70
     Bloch
    0.69
     thro
    0.69
    ައް
    0.69
    ములో
    0.67
     Nilsson
    0.67
    徹
    0.67
    但是我
    0.66
    POSITIVE LOGITS
    mechan
    0.59
     திருப்ப
    0.58
     Copern
    0.57
    inf
    0.55
    ვილი
    0.55
     gegen
    0.54
    ายน
    0.53
    GP
    0.52
    yuan
    0.52
     पुत्र
    0.51
    Activations Density 0.139%

    No Known Activations