© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106198
    Prev
    Next
    INDEX
    Explanations

    layout, flex, sizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     universally
    -0.85
    姹
    -0.85
    𝗎
    -0.84
     arbejde
    -0.80
    していました
    -0.78
    læg
    -0.78
     personalizar
    -0.76
     труд
    -0.76
    луч
    -0.74
    涕
    -0.74
    POSITIVE LOGITS
     ۱
    1.17
    flex
    1.17
     flex
    1.14
    initial
    0.96
    child
    0.92
    ample
    0.90
    none
    0.90
    grow
    0.90
    灵活
    0.84
    rageous
    0.84
    Activations Density 0.003%

    No Known Activations