© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 168542
    Prev
    Next
    INDEX
    Explanations

    windowing functions

    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
    
    0.45
    вались
    0.43
    ве
    0.42
     एक्सपेक्ट
    0.39
    رهای
    0.38
    _+
    0.38
    ಲಾಯಿತು
    0.38
    たっぷり
    0.37
    equivalent
    0.37
     }-
    0.36
    POSITIVE LOGITS
     apparently
    0.41
     surve
    0.40
     territorial
    0.39
     знаходиться
    0.38
     manag
    0.38
     sparkles
    0.38
     территориа
    0.38
     misses
    0.38
     seines
    0.38
     mentions
    0.37
    Activations Density 0.005%

    No Known Activations