© 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. 137484
    Prev
    Next
    INDEX
    Explanations

    Data costs

    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
     غم
    0.45
     sadde
    0.37
    쯜
    0.37
    agon
    0.36
    pointe
    0.36
     keren
    0.36
     физи
    0.36
     ограничен
    0.35
    顔
    0.35
     Насе
    0.35
    POSITIVE LOGITS
     deben
    0.41
     phải
    0.41
    ästä
    0.39
     rivalry
    0.38
     اجيب
    0.37
     indium
    0.37
     있어야
    0.37
     doivent
    0.37
     getString
    0.36
     xin
    0.36
    Activations Density 0.002%

    No Known Activations