© 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. 107713
    Prev
    Next
    INDEX
    Explanations

    words that appear in phrases

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

    product development

    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
    負担
    0.47
    💆
    0.47
    実行
    0.44
     deviates
    0.44
    гии
    0.43
    ロボ
    0.43
    ppies
    0.43
    aat
    0.43
    Standalone
    0.43
     deviate
    0.42
    POSITIVE LOGITS
     chiama
    0.51
     класи
    0.50
    MODE
    0.48
    @",
    0.47
    দেখিতে
    0.46
     দেখিয়া
    0.46
     नितिन
    0.46
     mùa
    0.46
    什么
    0.45
     نادر
    0.45
    Activations Density 0.001%

    No Known Activations