© 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. 130713
    Prev
    Next
    INDEX
    Explanations

    items followed by structure or movement

    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
     NSUTF
    0.45
    Flex
    0.44
     FLEX
    0.43
    柔软
    0.42
    噘
    0.42
     flexibility
    0.42
     Flexibility
    0.42
    tempHeader
    0.41
     flexibilidad
    0.41
    릅
    0.41
    POSITIVE LOGITS
     cop
    0.41
    ht
    0.37
    uci
    0.37
    &
    0.37
    vis
    0.37
     solutions
    0.37
    cc
    0.37
    col
    0.37
    kh
    0.36
    hline
    0.36
    Activations Density 0.001%

    No Known Activations