© 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. 188497
    Prev
    Next
    INDEX
    Explanations

    options and broader terms

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

    discussing / questions

    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
     शूटिंग
    0.52
    Ownership
    0.46
    彷
    0.46
    orsese
    0.45
     فقال
    0.44
    íme
    0.44
    ウダー
    0.44
    trong
    0.44
    erms
    0.43
    always
    0.43
    POSITIVE LOGITS
    Ми
    0.52
     arthritis
    0.50
    З
    0.50
    Си
    0.49
    День
    0.49
    Ш
    0.48
     spazio
    0.48
    Та
    0.47
     rubbed
    0.47
    Кон
    0.47
    Activations Density 0.001%

    No Known Activations