© 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. 101962
    Prev
    Next
    INDEX
    Explanations

    best practices, soil screening, hand washing, piercings

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

    explains or corrects information

    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
    TBL
    0.48
    莲
    0.47
    蓮
    0.47
    等待
    0.46
     পারিনি
    0.44
    潤
    0.44
    不同的
    0.43
    陨
    0.43
     ಧ
    0.43
     Amendment
    0.43
    POSITIVE LOGITS
    дение
    0.49
     encompasses
    0.48
     takes
    0.47
     explores
    0.47
     ведет
    0.47
     begins
    0.45
     führt
    0.45
     leads
    0.44
     ซ
    0.44
     arrives
    0.43
    Activations Density 0.000%

    No Known Activations