© 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. 551
    Prev
    Next
    INDEX
    Explanations

    multiple developers

    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
    jq
    0.49
     পেনশন
    0.48
     Epi
    0.47
     Infection
    0.47
    <0xA7>
    0.46
    عداد
    0.46
     交換
    0.44
     rade
    0.44
    right
    0.43
    ائل
    0.43
    POSITIVE LOGITS
    觉
    0.56
     suficient
    0.53
     substantive
    0.53
     develop
    0.52
     substantial
    0.52
     gerekli
    0.52
    ೂರ್ಣ
    0.52
     worthwhile
    0.51
     Theodore
    0.50
    不管
    0.49
    Activations Density 2.980%

    No Known Activations