© 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. 72024
    Prev
    Next
    INDEX
    Explanations

    terms 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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.41
     tercera
    -1.34
     doméstica
    -1.32
    зависи
    -1.30
    êts
    -1.27
    cisive
    -1.26
    vão
    -1.25
    鋦
    -1.25
    tifications
    -1.24
    🏉
    -1.23
    POSITIVE LOGITS
     other
    1.84
     more
    1.59
     about
    1.56
     a
    1.50
     numerous
    1.46
     no
    1.41
     new
    1.37
     there
    1.37
    อื่น
    1.36
    توض
    1.35
    Activations Density 0.105%

    No Known Activations