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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60034
    Prev
    Next
    INDEX
    Explanations

    matplotlib plotting

    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_34/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
     Trying
    -0.93
     or
    -0.92
    𝚎
    -0.88
    منى
    -0.86
    Ưu
    -0.84
    ým
    -0.84
     by
    -0.84
     prevent
    -0.83
     區
    -0.83
    enez
    -0.83
    POSITIVE LOGITS
     TITLE
    1.06
    figure
    1.01
    lovely
    0.99
     entré
    0.98
     GUIDE
    0.97
     acheter
    0.96
    _______________
    0.95
     illimit
    0.93
     magnifique
    0.93
     größe
    0.92
    Activations Density 0.001%

    No Known Activations