© 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. 32694
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     SIMILAR
    -1.19
    涧
    -1.11
     OPTIONAL
    -1.10
    érica
    -1.04
    similar
    -1.02
    举动
    -1.01
    鹵
    -0.99
     måte
    -0.98
    物は
    -0.98
     would
    -0.98
    POSITIVE LOGITS
     one
    1.34
    越高
    1.09
     single
    1.06
    Different
    1.05
     ones
    1.05
    Others
    1.03
     jornalista
    1.03
     smaller
    1.01
    কে
    0.99
     size
    0.98
    Activations Density 0.077%

    No Known Activations