© 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. 98795
    Prev
    Next
    INDEX
    Explanations

    a bunch of

    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
     such
    -1.66
     though
    -1.40
     have
    -1.35
    篠
    -1.27
     aunque
    -1.27
     although
    -1.25
     energético
    -1.21
     „
    -1.21
     sufficient
    -1.18
    though
    -1.17
    POSITIVE LOGITS
     rafraî
    1.41
     rafra
    1.27
    klere
    1.19
     Sebuah
    1.17
     Strukt
    1.16
     trener
    1.16
     plafon
    1.14
    ₾
    1.14
     paljon
    1.12
    ροφο
    1.12
    Activations Density 0.124%

    No Known Activations