© 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. 4650
    Prev
    Next
    INDEX
    Explanations

    Thank you

    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
     aank
    0.70
    лізації
    0.69
    SHRI
    0.69
    estä
    0.69
    ###########
    0.68
    éis
    0.68
    itaria
    0.68
    ۣ
    0.68
     Pole
    0.67
     nummer
    0.67
    POSITIVE LOGITS
    indsight
    0.66
    鲞
    0.61
    皆様
    0.61
    so
    0.59
     promoc
    0.57
    dan
    0.57
     containment
    0.57
    苋
    0.57
     concludes
    0.56
     ভাগ্য
    0.56
    Activations Density 0.048%

    No Known Activations