© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 19407
    Prev
    Next
    INDEX
    Explanations

    embassy or consulate, universities and research

    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
    ५
    0.94
    ३
    0.94
    ۴
    0.93
     Wuhan
    0.91
     Shandong
    0.90
     México
    0.88
     આવા
    0.87
     Cancun
    0.87
    ۵
    0.85
     Maharashtra
    0.85
    POSITIVE LOGITS
    čaj
    0.67
     ẩn
    0.66
    ปัจ
    0.66
    에도
    0.64
    レビ
    0.64
     appreciate
    0.63
     pesc
    0.63
    τισ
    0.63
    했을
    0.63
    alay
    0.63
    Activations Density 0.000%

    No Known Activations