© 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. 192187
    Prev
    Next
    INDEX
    Explanations

    physical actions and concepts

    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
    ibilités
    0.40
     آئینے
    0.39
     গৌর
    0.38
     بلوچستان
    0.38
     বাঙ্গালা
    0.37
    ☠
    0.37
     общем
    0.36
    汰
    0.36
     sparsim
    0.36
    PathTemplate
    0.35
    POSITIVE LOGITS
     contribution
    0.42
     reduced
    0.42
     contraction
    0.42
    ën
    0.40
     ant
    0.39
     mett
    0.38
     interaction
    0.38
     optional
    0.38
     reduction
    0.37
     temporary
    0.37
    Activations Density 0.002%

    No Known Activations