© 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. 69689
    Prev
    Next
    INDEX
    Explanations

    native English speakers

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

    backup your system

    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
     tourists
    0.45
     ایرانی
    0.44
    ===
    0.42
    iiii
    0.41
     éta
    0.41
    اگ
    0.40
    interview
    0.40
     emper
    0.40
     də
    0.40
    메라
    0.40
    POSITIVE LOGITS
    дей
    0.51
    进步
    0.49
     cadeia
    0.46
     BUT
    0.46
    丳
    0.45
    ęs
    0.44
    耘
    0.44
     But
    0.42
     зовніш
    0.42
     сосредото
    0.42
    Activations Density 0.001%

    No Known Activations