© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128579
    Prev
    Next
    INDEX
    Explanations

    purpose of use

    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
    aneity
    -1.66
     komik
    -1.63
    粜
    -1.63
     usar
    -1.54
     manualidades
    -1.52
    跸
    -1.52
    
    -1.51
     memakai
    -1.50
     muñ
    -1.50
    ✬
    -1.48
    POSITIVE LOGITS
     to
    2.86
     in
    2.78
     for
    1.87
     Even
    1.68
     and
    1.68
     Not
    1.64
     These
    1.52
     first
    1.52
     Today
    1.48
    s
    1.39
    Activations Density 0.097%

    No Known Activations