© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10509
    Prev
    Next
    INDEX
    Explanations

    tab and tap words

    np_acts-logits-general · gemini-2.5-flash-lite

    interface tabs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ㉖
    0.39
     dto
    0.38
    riven
    0.38
    tre
    0.36
     Highly
    0.36
    zai
    0.36
    शल
    0.36
    言
    0.36
     Built
    0.35
     Actions
    0.35
    POSITIVE LOGITS
     tab
    1.06
     TAB
    1.05
     Tab
    1.02
    Tab
    1.00
    TAB
    0.99
    tab
    0.91
    tabname
    0.89
     tabulation
    0.81
    タブ
    0.80
     tabb
    0.79
    Activations Density 0.061%

    No Known Activations