© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22420
    Prev
    Next
    INDEX
    Explanations

    function definitions and programming code

    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
     クリスマス
    0.42
     ഇരു
    0.40
    ृति
    0.40
     célèbre
    0.39
    同學們
    0.39
     दिवाली
    0.39
    ='/'
    0.38
     blancas
    0.38
    orgetown
    0.37
     탐
    0.37
    POSITIVE LOGITS
    ˌ
    0.48
     _
    0.48
     Corresponding
    0.43
     correspondiente
    0.42
     corresponding
    0.41
     Mgr
    0.40
     Pem
    0.39
    \_
    0.38
     SMB
    0.37
     *_
    0.37
    Activations Density 0.028%

    No Known Activations