© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 26343
    Prev
    Next
    INDEX
    Explanations

    cmake and build arguments

    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
    Negative Logits
    పర
    0.44
     families
    0.40
    ouin
    0.39
     Juel
    0.37
    ঙালি
    0.37
     एस्ट्र
    0.37
    erase
    0.36
     বয়স
    0.36
    带宽
    0.36
    ⓐ
    0.36
    POSITIVE LOGITS
    COMMAND
    0.39
     COMMAND
    0.38
     läh
    0.38
     thuyết
    0.38
    誠
    0.37
    হাস
    0.37
    Bruce
    0.37
    MAKE
    0.36
    滸
    0.36
    乗り
    0.36
    Activations Density 0.000%

    No Known Activations