© 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. 35947
    Prev
    Next
    INDEX
    Explanations

    PEP array formulas

    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
    十一章
    0.42
     বর্ণনা
    0.38
     Watering
    0.37
    ransform
    0.37
     ‘
    0.36
     Serbia
    0.36
     Sham
    0.36
    이니까
    0.36
     .”
    0.36
    𓇼
    0.36
    POSITIVE LOGITS
    ০০০
    0.39
    absol
    0.38
    ≾
    0.38
     ತುಂಬ
    0.37
    igger
    0.36
     अणु
    0.36
    student
    0.35
    udiant
    0.35
    fuels
    0.35
    symmetric
    0.35
    Activations Density 0.000%

    No Known Activations