© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8913
    Prev
    Next
    INDEX
    Explanations

    times and dates

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

    top_p nucleus sampling

    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_40_width_16k_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
     sonrisa
    0.43
    
    0.42
    ไฟฟ้า
    0.41
    Electronic
    0.39
     electrónica
    0.39
    ราช
    0.38
    手机
    0.38
    یدی
    0.38
    Directories
    0.37
    袜子
    0.37
    POSITIVE LOGITS
     WIB
    0.42
     ー
    0.41
     輸入
    0.40
     Giulio
    0.40
     Dopo
    0.38
     αντι
    0.38
     posticis
    0.38
    after
    0.38
    Oe
    0.38
     વા
    0.38
    Activations Density 0.011%

    No Known Activations