© 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. 22-GEMMASCOPE-RES-131K
    7. 24905
    Prev
    Next
    INDEX
    Explanations

    other

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    licópter
    -1.05
    总之
    -1.01
     ....
    -0.99
     .....
    -0.99
     है
    -0.93
    原理
    -0.92
    。。
    -0.91
    ........
    -0.90
     照明
    -0.90
     zarówno
    -0.89
    POSITIVE LOGITS
     others
    1.44
     other
    1.40
     остальные
    1.31
     also
    1.20
     then
    1.14
    others
    1.14
     daarna
    1.09
     anderer
    1.09
     néanmoins
    1.09
     lainnya
    1.07
    Activations Density 0.115%

    No Known Activations