© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66867
    Prev
    Next
    INDEX
    Explanations

    contrasting attributes and quantities

    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_22/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
    ிகள்
    -0.91
     насеља
    -0.85
     désert
    -0.81
    nología
    -0.80
    sión
    -0.79
    чек
    -0.79
    itively
    -0.77
     poème
    -0.77
    фаль
    -0.77
    Sziasztok
    -0.76
    POSITIVE LOGITS
     but
    3.05
     yet
    2.69
    Yet
    1.93
    yet
    1.92
     while
    1.88
     Yet
    1.87
     nhưng
    1.57
     namun
    1.54
     mientras
    1.52
     YET
    1.46
    Activations Density 0.080%

    No Known Activations