© 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. 145
    Prev
    Next
    INDEX
    Explanations

    inexpensive and beginner items

    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
     elegant
    0.47
     elegantly
    0.46
     Luxurious
    0.46
    优雅
    0.46
     nuanced
    0.45
     elegan
    0.42
     elegante
    0.42
     erud
    0.41
    峯
    0.41
     luxurious
    0.41
    POSITIVE LOGITS
     cheap
    1.60
    cheap
    1.41
     cheapest
    1.37
     inexpensive
    1.37
    Cheap
    1.34
     cheaply
    1.31
     Cheap
    1.30
     सस्ते
    1.30
     деше
    1.29
     cheaper
    1.23
    Activations Density 0.107%

    No Known Activations