© 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. 228300
    Prev
    Next
    INDEX
    Explanations

    training and capacity building

    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
    不存在
    0.49
    不是
    0.48
     sucks
    0.48
    棵
    0.46
     occurred
    0.45
     breast
    0.45
     ecl
    0.45
     Secondo
    0.44
    不容易
    0.43
    ével
    0.43
    POSITIVE LOGITS
     Verantwortung
    0.53
    ilität
    0.49
     finiteness
    0.49
     ಗೌ
    0.49
    โต
    0.46
    finite
    0.45
     يت
    0.45
     অনুগ্রহ
    0.45
    지
    0.45
     বিশেষভাবে
    0.44
    Activations Density 0.001%

    No Known Activations