© 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. 20639
    Prev
    Next
    INDEX
    Explanations

    with me or related phrases

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

    URLs with numbers

    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
    zelfde
    0.37
     alcuna
    0.36
    ش
    0.35
     invece
    0.35
    ون
    0.35
     erstmals
    0.35
     stesso
    0.34
    شهر
    0.33
     pasada
    0.33
    والی
    0.33
    POSITIVE LOGITS
     ListView
    0.39
    ೀವ
    0.37
    小学生
    0.36
    本身的
    0.35
     제목
    0.34
    ете
    0.34
    안녕하세요
    0.34
    燥
    0.34
    ແລະ
    0.33
    カテゴリ
    0.33
    Activations Density 0.042%

    No Known Activations