© 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. 157120
    Prev
    Next
    INDEX
    Explanations

    non-english script and words

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

    Local script, avoid contamination

    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
    '
    0.57
     berapa
    0.49
     fortress
    0.48
     life
    0.46
     factory
    0.46
     porridge
    0.46
     warehouse
    0.46
     Fortress
    0.46
     kapan
    0.46
     persegi
    0.46
    POSITIVE LOGITS
    শিক্ষ
    0.52
     இந்திய
    0.52
     אח
    0.51
    शिक्
    0.48
     قابلیت
    0.48
     `:`,
    0.48
     নিম্ন
    0.47
     ദിവ
    0.47
     صلاحیت
    0.47
    ત
    0.46
    Activations Density 0.001%

    No Known Activations