© 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. 1475
    Prev
    Next
    INDEX
    Explanations

    arguments after colons or commas

    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
    kepsilon
    0.39
     빨리
    0.39
    鈽
    0.36
    大な
    0.36
    zem
    0.36
    曲線
    0.35
    วิ่ง
    0.35
     واقعی
    0.35
    ক্ষিতে
    0.35
    捧
    0.35
    POSITIVE LOGITS
     Wür
    0.40
     pres
    0.39
    Wür
    0.37
     ['
    0.35
    ωσης
    0.35
     deflect
    0.34
    object
    0.34
     ED
    0.34
     Pres
    0.34
     indiv
    0.34
    Activations Density 0.002%

    No Known Activations