© 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. 10-GEMMASCOPE-RES-131K
    7. 45544
    Prev
    Next
    INDEX
    Explanations

    brands or place names

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     it
    -2.09
     by
    -1.83
     there
    -1.59
     a
    -1.49
     an
    -1.49
     one
    -1.46
     February
    -1.43
     more
    -1.41
    着一个
    -1.39
    闕
    -1.39
    POSITIVE LOGITS
     hvil
    1.66
     visse
    1.64
     spion
    1.60
    THEY
    1.59
     menyen
    1.52
     bluse
    1.49
     kado
    1.47
    踯
    1.45
     eene
    1.43
     abonnement
    1.43
    Activations Density 0.342%

    No Known Activations