© 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. 203578
    Prev
    Next
    INDEX
    Explanations

    lego bricks

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

    optimize listings

    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
    밂
    0.57
    ricies
    0.55
     সামনের
    0.55
     покер
    0.53
     зона
    0.53
     Конгрегация
    0.51
     Бүгенге
    0.51
    பிலோ
    0.50
     Цуки
    0.50
    webBrowser
    0.50
    POSITIVE LOGITS
    ire
    0.48
     en
    0.47
     sustainability
    0.46
     cr
    0.46
     may
    0.44
    š
    0.43
    ב
    0.43
    มูล
    0.43
     never
    0.43
     employ
    0.42
    Activations Density 0.001%

    No Known Activations