© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 112541
    Prev
    Next
    INDEX
    Explanations

    interviewed by, arts traditions

    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_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
    פ
    0.48
    缡
    0.48
    п
    0.44
    ೯
    0.44
     белару
    0.44
    ία
    0.44
     tehát
    0.43
    ጵ
    0.43
    উন্ড
    0.42
     коле
    0.42
    POSITIVE LOGITS
    atsuki
    0.50
    fun
    0.47
    VS
    0.46
    var
    0.46
    mos
    0.46
    hy
    0.46
    search
    0.45
    varia
    0.45
    在此
    0.45
     irradiated
    0.44
    Activations Density 0.003%

    No Known Activations