© 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. 107288
    Prev
    Next
    INDEX
    Explanations

    and thanks

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

    recommendations and advice

    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
     הר
    0.50
     BR
    0.47
     {
    0.45
     جميع
    0.45
     Р
    0.45
     الر
    0.43
     vb
    0.43
     jo
    0.43
     fram
    0.43
     wall
    0.42
    POSITIVE LOGITS
    全新
    0.51
     supremely
    0.49
    subprocess
    0.48
     अद्वितीय
    0.47
    深
    0.47
    linkedin
    0.47
    你自己
    0.46
    enapi
    0.46
    менова
    0.45
    fantastic
    0.45
    Activations Density 0.002%

    No Known Activations