© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 26204
    Prev
    Next
    INDEX
    Explanations

    click on, @gmail

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

    histories of, Text panel

    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_31_width_262k_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
     ۳
    0.54
     ۴
    0.52
     እንኳን
    0.48
     head
    0.47
    rakk
    0.47
     full
    0.46
     soiled
    0.46
     risk
    0.45
     ۵
    0.45
     PAR
    0.45
    POSITIVE LOGITS
    笑道
    0.53
     samoglas
    0.52
    叅
    0.49
     desempeñ
    0.48
    परे
    0.47
     Egyes
    0.47
    า
    0.47
    亣
    0.47
    ยาย
    0.47
    ertown
    0.46
    Activations Density 0.000%

    No Known Activations