© 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. 22537
    Prev
    Next
    INDEX
    Explanations

    followed by

    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
     this
    -2.09
     these
    -1.95
     has
    -1.92
     while
    -1.80
     now
    -1.77
     people
    -1.69
     time
    -1.63
     before
    -1.60
     not
    -1.59
     already
    -1.55
    POSITIVE LOGITS
     solides
    1.73
    hauled
    1.65
     allerlei
    1.59
     illustre
    1.58
    𓆏
    1.55
     rafra
    1.55
     autonomie
    1.55
     faciliter
    1.55
     unſ
    1.54
     autonome
    1.53
    Activations Density 0.042%

    No Known Activations