© 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. 128494
    Prev
    Next
    INDEX
    Explanations

    completed it

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

    preparing secure generation zones

    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
     {
    0.47
     ENGINE
    0.46
     свой
    0.46
     |\
    0.45
    Como
    0.45
    MainActivityTest
    0.45
    bk
    0.44
     досто
    0.44
    AIN
    0.43
     kingdom
    0.42
    POSITIVE LOGITS
    膿
    0.48
     pneumoniae
    0.47
    懼
    0.47
     রাজনৈতিক
    0.47
     ماضی
    0.46
     verteilt
    0.46
    ání
    0.44
    穩定
    0.44
    不安定
    0.43
    營養
    0.43
    Activations Density 0.001%

    No Known Activations