© 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. 204931
    Prev
    Next
    INDEX
    Explanations

    evaluating performance/models

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

    tax system complexity

    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
    岨
    0.53
    ಹು
    0.50
    łej
    0.48
    ي
    0.48
     мра
    0.47
    મ
    0.47
     GIL
    0.46
     eliminar
    0.45
     এছাড়া
    0.45
     Фі
    0.45
    POSITIVE LOGITS
    体制
    0.47
    model
    0.47
    こちらの
    0.47
     development
    0.46
    模式
    0.45
     saint
    0.45
    こちら
    0.45
     facade
    0.44
    惜
    0.44
     ধাঁ
    0.43
    Activations Density 0.000%

    No Known Activations