© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11413
    Prev
    Next
    INDEX
    Explanations

    path to file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    0.29
     pedagogy
    0.26
    ती
    0.26
    лъ
    0.25
    ம
    0.25
    يي
    0.25
    لا
    0.24
     academia
    0.24
     translation
    0.24
     ambassadors
    0.24
    POSITIVE LOGITS
     اقصیٰ
    0.30
     Кан
    0.26
     :=\
    0.26
     Prothorax
    0.26
     곳
    0.26
     ໜອງ
    0.25
    блон
    0.25
     ನೀಡ
    0.25
     স্টোন
    0.25
     Citt
    0.24
    Activations Density 0.001%

    No Known Activations