© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11852
    Prev
    Next
    INDEX
    Explanations

    variable name assignment or placeholder

    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_31_width_16k_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
     and
    0.53
     which
    0.48
    0.47
     Korean
    0.44
     a
    0.43
     the
    0.43
     American
    0.40
     olan
    0.40
    ↵
    0.40
     Copyright
    0.40
    POSITIVE LOGITS
    ллі
    0.44
    Bechyné
    0.43
    לו
    0.40
     גם
    0.39
     கெல்
    0.39
     Еўро
    0.39
     فولت
    0.39
    Geschichte
    0.38
     Володи
    0.38
    תיים
    0.38
    Activations Density 0.286%

    No Known Activations