© 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. 192135
    Prev
    Next
    INDEX
    Explanations

    body parts and computing resources

    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
     раньше
    0.45
     اقول
    0.40
     सोर्स
    0.39
     Unfortunately
    0.38
     Đúng
    0.38
    騏
    0.38
     prothorax
    0.38
    ুতি
    0.38
    늙
    0.37
    precipitation
    0.37
    POSITIVE LOGITS
     crucially
    0.39
    iemann
    0.37
    ಾ
    0.37
    witz
    0.35
    AlignedText
    0.35
    "?>
    0.35
    Alles
    0.35
    মানে
    0.34
    ahlen
    0.34
     playlists
    0.34
    Activations Density 0.001%

    No Known Activations