© 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. 27870
    Prev
    Next
    INDEX
    Explanations

    tables with multi-lingual labels

    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
    brandt
    0.38
    ---|
    0.38
    IDENCE
    0.38
     ಬಾರಿ
    0.38
    ^{*}$
    0.37
    Pert
    0.37
    大家好
    0.35
    াস
    0.35
    -----+
    0.35
    ASD
    0.34
    POSITIVE LOGITS
     Windows
    0.42
     জানালা
    0.39
     organising
    0.38
     Eurovision
    0.38
     Yeşil
    0.38
     올
    0.37
     заня
    0.37
    Windows
    0.37
     ملف
    0.37
     शेष
    0.36
    Activations Density 0.013%

    No Known Activations