© 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. 21664
    Prev
    Next
    INDEX
    Explanations

    jetpack compose, foundation, ui

    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
     cakkh
    0.45
    ლო
    0.41
    мино
    0.41
    жаем
    0.40
    жаю
    0.38
    ॉर्ट
    0.38
    꺅
    0.38
    median
    0.37
     cortic
    0.37
    embal
    0.37
    POSITIVE LOGITS
     Foundation
    0.55
    ui
    0.54
     material
    0.50
    Foundation
    0.48
    UI
    0.47
    💧
    0.47
     Material
    0.47
     UI
    0.46
    foundation
    0.46
     foundation
    0.45
    Activations Density 0.001%

    No Known Activations