© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13288
    Prev
    Next
    INDEX
    Explanations

    food and international places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
    ্লেখ
    0.94
    運転
    0.90
     تجي
    0.90
     *:
    0.79
    arif
    0.79
    ladi
    0.79
     onders
    0.78
    覧
    0.76
    خستان
    0.76
    ulele
    0.75
    POSITIVE LOGITS
     मूर्त
    0.69
    एमएस
    0.64
     سے
    0.64
     MS
    0.64
    {~
    0.62
     से
    0.61
    ИК
    0.60
     ਤੋਂ
    0.58
     전
    0.58
    য়ে
    0.57
    Activations Density 0.002%

    No Known Activations