© 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. 41-GEMMASCOPE-2-RES-262K
    7. 30154
    Prev
    Next
    INDEX
    Explanations

    alcohols, halides, ketone, aldehyde, nucle

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     hydrogen
    0.58
    hydrogen
    0.53
    Hydrogen
    0.50
    氢
    0.49
     Hydrogen
    0.48
    水素
    0.46
     hydrogenation
    0.44
     Diels
    0.44
     हाइड्रोजन
    0.44
     benzene
    0.43
    POSITIVE LOGITS
     nucle
    0.65
     alcohols
    0.52
     halides
    0.52
    腧
    0.52
    nucle
    0.50
     തയ്യാ
    0.48
    ScriptInterface
    0.46
    Nucle
    0.46
     substrate
    0.46
     nuclé
    0.44
    Activations Density 0.007%

    No Known Activations