© 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-65K
    7. 6285
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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_65k_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
     분명
    0.41
    PlatformVersion
    0.38
    恣
    0.38
     calendário
    0.37
    ScreenBinding
    0.37
     बैठा
    0.36
    ัญญา
    0.36
    艨
    0.35
     eccles
    0.35
    โทษ
    0.35
    POSITIVE LOGITS
    "]));
    0.50
    ورك
    0.39
     cerr
    0.39
     fresh
    0.38
     formerly
    0.38
    empre
    0.38
    كله
    0.38
    ம
    0.38
     motorcycl
    0.38
     stati
    0.36
    Activations Density 0.038%

    No Known Activations