© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11947
    Prev
    Next
    INDEX
    Explanations

    find a

    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_31_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
    ဖို့
    0.47
     মানে
    0.45
     ame
    0.44
     jo
    0.44
    即将
    0.44
     Triumph
    0.43
    勒
    0.43
    仿佛
    0.43
    သွား
    0.43
    ကျွန်
    0.43
    POSITIVE LOGITS
     isoniazid
    0.45
     ट्रै
    0.45
    ồ
    0.44
    ό
    0.44
     высоким
    0.44
    ường
    0.43
     カメラ
    0.43
     선정
    0.43
    Medic
    0.42
    ְ
    0.42
    Activations Density 0.002%

    No Known Activations