© 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. 100380
    Prev
    Next
    INDEX
    Explanations

    "há", "existe", "tienen", "tenho", "нет, было"

    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
    苤
    -2.50
    leggio
    -2.41
     ALSO
    -2.39
    饪
    -2.31
     插图
    -2.28
    渽
    -2.28
    
    -2.25
    臜
    -2.23
    鹋
    -2.20
    涐
    -2.19
    POSITIVE LOGITS
     which
    2.53
     of
    2.17
     in
    1.98
     additional
    1.83
     one
    1.83
     Why
    1.82
     but
    1.79
     any
    1.78
     Both
    1.77
     information
    1.76
    Activations Density 0.006%

    No Known Activations