© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192941
    Prev
    Next
    INDEX
    Explanations

    add involving spills

    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
     পত্রিকা
    0.45
     rétréc
    0.45
    ด้
    0.38
    レンジ
    0.37
     الحالي
    0.37
    镓
    0.36
     variété
    0.35
    ಸ್‌
    0.35
     élast
    0.35
     mètre
    0.35
    POSITIVE LOGITS
     Damen
    0.45
    েন
    0.44
     Impulse
    0.42
    щие
    0.41
    LN
    0.41
    μοσ
    0.41
     Не
    0.41
    ="../
    0.40
    ন্ধে
    0.40
    ieval
    0.40
    Activations Density 0.000%

    No Known Activations