© 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. 4675
    Prev
    Next
    INDEX
    Explanations

    body {

    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
     terminou
    0.73
    пас
    0.72
     dezvolt
    0.72
     mile
    0.71
    internal
    0.69
    扁
    0.69
     Aki
    0.67
    یکل
    0.66
    Arrows
    0.65
     সাক্ষাৎকার
    0.64
    POSITIVE LOGITS
     Relaxation
    0.77
     Regal
    0.73
    ولة
    0.73
     Lack
    0.73
     getString
    0.70
     Flavor
    0.70
     relaxation
    0.69
    oretto
    0.68
    lore
    0.67
    ⣤
    0.65
    Activations Density 0.024%

    No Known Activations