© 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. 11673
    Prev
    Next
    INDEX
    Explanations

    Go to tab

    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
    uximab
    0.40
     macular
    0.38
    pedido
    0.36
    缽
    0.36
    minic
    0.36
    يا
    0.36
     वगैर
    0.35
    霞
    0.35
    فيذ
    0.35
    一道
    0.34
    POSITIVE LOGITS
     tab
    2.13
     tabs
    1.86
     Tab
    1.84
    Tab
    1.78
    tab
    1.77
     Tabs
    1.63
    タブ
    1.59
    tabs
    1.53
    Tabs
    1.52
     TAB
    1.52
    Activations Density 0.024%

    No Known Activations