© 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. 12809
    Prev
    Next
    INDEX
    Explanations

    math operator

    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
     histological
    0.46
    ্যন্তরীণ
    0.45
    ।’’
    0.44
    ।''
    0.44
    ।]
    0.42
    orragie
    0.42
     النصوص
    0.42
    〢
    0.42
     डॉक्यूमेंट्री
    0.42
    "),],
    0.40
    POSITIVE LOGITS
     {
    0.42
    acket
    0.41
           
    0.40
            
    0.40
    {
    0.39
     End
    0.39
     pass
    0.38
    mrow
    0.38
     Pass
    0.38
     T
    0.37
    Activations Density 0.004%

    No Known Activations