© 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. 58329
    Prev
    Next
    INDEX
    Explanations

    it's

    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
    Not in Any Lists

    No Comments

    Negative Logits
    犼
    -1.91
    側から
    -1.82
     området
    -1.73
     тільки
    -1.68
    也会
    -1.66
     :/
    -1.65
     dette
    -1.64
     meubles
    -1.62
     пошли
    -1.61
    玙
    -1.61
    POSITIVE LOGITS
     own
    2.98
     in
    1.97
     touted
    1.91
    𖣘
    1.76
     fotografias
    1.65
    ,
    1.59
     abilities
    1.57
     a
    1.56
     ability
    1.55
    self
    1.55
    Activations Density 0.040%

    No Known Activations