© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111564
    Prev
    Next
    INDEX
    Explanations

    efficiency and performance metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     анима
    0.38
     Margherita
    0.37
     উল্লেখযোগ্য
    0.37
     squint
    0.37
    쩌
    0.36
    推出
    0.36
    厂商
    0.35
    娯
    0.35
     Ched
    0.35
     দখলে
    0.35
    POSITIVE LOGITS
     એટલે
    0.38
    $}
    0.38
     moistened
    0.37
     ურთიერთ
    0.37
    <unused0>
    0.37
    nPort
    0.37
    räger
    0.36
    !!");
    0.36
    auten
    0.36
    nance
    0.35
    Activations Density 0.005%

    No Known Activations