© 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. 1432
    Prev
    Next
    INDEX
    Explanations

    C followed by #, ., -, or ric

    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
    득
    0.61
    อม
    0.55
     tread
    0.55
     below
    0.54
     پڑ
    0.53
    rounded
    0.53
    骐
    0.52
    ดูก
    0.52
    回り
    0.52
     under
    0.52
    POSITIVE LOGITS
     take
    0.62
    level
    0.60
     বিদ্রোহী
    0.60
    部队
    0.60
    qdm
    0.59
     Kunde
    0.59
    kale
    0.58
    take
    0.58
    Taking
    0.57
    Ќ
    0.57
    Activations Density 0.623%

    No Known Activations