© 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. 3017
    Prev
    Next
    INDEX
    Explanations

    abstract data structures

    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
    疾患
    0.36
     unrel
    0.35
     bioactive
    0.35
     parenteral
    0.35
     PMID
    0.33
     contralateral
    0.33
     recid
    0.32
     seminal
    0.32
    🈚
    0.32
    陘
    0.32
    POSITIVE LOGITS
     cupcakes
    0.80
     balloons
    0.73
     sunflowers
    0.72
     cupcake
    0.71
     bananas
    0.68
     muffins
    0.66
     rainbow
    0.65
     rainbows
    0.65
     pumpkins
    0.65
     Balloons
    0.64
    Activations Density 0.176%

    No Known Activations