© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22496
    Prev
    Next
    INDEX
    Explanations

    dates, times, or IP addresses

    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
    म्
    0.40
    ம்பெ
    0.40
     പാര്‍
    0.37
     Eduard
    0.37
    𒌋
    0.37
    ૪
    0.37
    िता
    0.36
     YAP
    0.36
     tableau
    0.36
    ☓
    0.35
    POSITIVE LOGITS
    ationale
    0.37
     بعدها
    0.37
     потім
    0.35
    되었
    0.34
     পরেও
    0.33
    上映
    0.32
    ahanam
    0.32
     دوسرا
    0.32
     อื่น
    0.32
    消防
    0.31
    Activations Density 0.014%

    No Known Activations