© 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. 209920
    Prev
    Next
    INDEX
    Explanations

    technical phrases and concepts

    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
     ха
    0.38
    ֶ
    0.37
     rework
    0.36
     njima
    0.36
    SelectedItem
    0.35
    ハ
    0.35
     consuming
    0.34
     ინ
    0.34
    チン
    0.33
    [-\
    0.33
    POSITIVE LOGITS
     koş
    0.47
    jab
    0.42
    姏
    0.41
     понятия
    0.40
     taches
    0.39
     Soto
    0.39
     Pairs
    0.39
    ційний
    0.38
    ems
    0.38
    pstmt
    0.38
    Activations Density 0.000%

    No Known Activations