© 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. 34-GEMMASCOPE-RES-131K
    7. 91858
    Prev
    Next
    INDEX
    Explanations

    html tags and introductory words

    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
    出来ない
    -0.89
     by
    -0.84
     probably
    -0.83
     any
    -0.81
    جع
    -0.79
    福建
    -0.79
     camera
    -0.78
    radan
    -0.78
     APPELLATE
    -0.77
    dieran
    -0.77
    POSITIVE LOGITS
     étudier
    1.01
     cliquant
    0.96
    ,</
    0.94
     BEAUTIFUL
    0.92
     beaut
    0.91
    ;</
    0.90
    awtextra
    0.88
     Largest
    0.87
     AMAZING
    0.87
     unden
    0.87
    Activations Density 0.000%

    No Known Activations