© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203290
    Prev
    Next
    INDEX
    Explanations

    materials, payment, injuries, logistics

    np_acts-logits-general · gemini-2.5-flash-lite

    futures contracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     essayer
    0.44
    대에
    0.42
    뮤
    0.42
    떨
    0.42
    덮
    0.42
    白い
    0.41
    㡺
    0.41
    フォ
    0.41
    उनकी
    0.41
     enseñ
    0.41
    POSITIVE LOGITS
     参数
    0.46
     Materials
    0.44
     আসা
    0.44
     অংশগ্রহণ
    0.43
     পাঠক
    0.42
     katıl
    0.42
     নীতিমালা
    0.42
     Fabrics
    0.41
     participating
    0.41
    جان
    0.41
    Activations Density 0.001%

    No Known Activations