© 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. 10135
    Prev
    Next
    INDEX
    Explanations

    numbered lists and items

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

    marked lists or structured text

    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
    ঃ
    0.39
     يدل
    0.38
    删除
    0.37
    讲解
    0.35
     useCustom
    0.35
     删除
    0.35
    льзя
    0.34
    ೩
    0.34
     व्याख्या
    0.34
    下列
    0.34
    POSITIVE LOGITS
    парт
    0.42
     Nih
    0.39
     pe
    0.36
     galore
    0.36
     anda
    0.36
     nih
    0.36
     fraught
    0.35
    ​​​​
    0.35
     Jov
    0.35
     artis
    0.34
    Activations Density 0.001%

    No Known Activations