© 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. 36688
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence tasks

    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
     destinés
    0.44
    ֨
    0.42
     shen
    0.41
    ແມ່ນ
    0.41
     chargés
    0.39
     जनरल
    0.39
     directorial
    0.39
     метою
    0.39
     enviados
    0.38
     destinée
    0.38
    POSITIVE LOGITS
    ://"
    0.43
    ilios
    0.39
    artificial
    0.38
    abile
    0.36
    Artificial
    0.36
    ematic
    0.35
     subst
    0.34
     artificial
    0.34
    قیم
    0.34
     artificially
    0.34
    Activations Density 0.000%

    No Known Activations