© 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. 163859
    Prev
    Next
    INDEX
    Explanations

    specific purpose

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

    types of relationships and roles

    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
     ভিট
    0.58
    ิทธิภาพ
    0.54
     상담
    0.52
     Nutritional
    0.51
    相談
    0.50
    養成
    0.48
     vorhand
    0.48
    竑
    0.46
    AsAction
    0.46
     클래
    0.46
    POSITIVE LOGITS
     confined
    0.47
     definitively
    0.45
     conclusively
    0.45
    第二次
    0.45
    igrants
    0.44
    ➳
    0.44
    .............
    0.43
    queens
    0.43
     GRA
    0.43
    rs
    0.43
    Activations Density 0.001%

    No Known Activations