© 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. 128658
    Prev
    Next
    INDEX
    Explanations

    gzip and compression libraries

    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
     knows
    -1.76
     know
    -1.73
     Then
    -1.68
    它是
    -1.59
     says
    -1.59
     You
    -1.58
     what
    -1.58
    秉
    -1.52
     was
    -1.52
    
    -1.48
    POSITIVE LOGITS
    0
    1.80
    6
    1.77
    3
    1.70
    ти
    1.59
     verborgen
    1.56
    gzip
    1.52
    拶
    1.52
    塍
    1.52
    chenta
    1.51
     parachoque
    1.46
    Activations Density 0.007%

    No Known Activations