© 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. 59601
    Prev
    Next
    INDEX
    Explanations

    unit testing frameworks

    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
     There
    -1.78
     Another
    -1.67
     would
    -1.63
     Often
    -1.54
     When
    -1.50
     However
    -1.48
     Once
    -1.44
     Sometimes
    -1.41
     Regarding
    -1.41
     umana
    -1.40
    POSITIVE LOGITS
    泐
    1.48
    事は
    1.45
    ":
    1.40
    
    1.39
     hereafter
    1.38
     gleiche
    1.38
    
    1.37
    țiunea
    1.37
    ());
    1.36
    λι
    1.35
    Activations Density 0.042%

    No Known Activations