© 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. 240661
    Prev
    Next
    INDEX
    Explanations

    falling all

    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
    结构
    0.39
     প্রতিষ্ঠাতা
    0.39
    자들이
    0.39
    很重要
    0.39
    scrollTo
    0.38
     đại
    0.38
     протяжении
    0.38
    ং
    0.38
    ARGET
    0.37
     khí
    0.37
    POSITIVE LOGITS
    tiene
    0.42
     faculté
    0.40
     childlike
    0.40
    Jud
    0.39
    მი
    0.38
     בנו
    0.38
    jud
    0.38
     Wiss
    0.38
     endearing
    0.37
    0
    0.37
    Activations Density 0.000%

    No Known Activations