© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138590
    Prev
    Next
    INDEX
    Explanations

    governance and actions

    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_16_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
     enquanto
    0.57
     svilupp
    0.56
    谦
    0.56
     quizás
    0.53
     dünyaya
    0.53
     शे
    0.51
     siendo
    0.51
     jako
    0.51
    罗
    0.51
    带动
    0.50
    POSITIVE LOGITS
     files
    0.60
     buses
    0.56
    ז
    0.55
    Ы
    0.54
    ის
    0.52
    ת
    0.52
     вполне
    0.51
    ר
    0.49
     ორგანო
    0.49
    ח
    0.49
    Activations Density 0.080%

    No Known Activations