© 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. 10-GEMMASCOPE-RES-131K
    7. 43129
    Prev
    Next
    INDEX
    Explanations

    percentages, years, miles, inches

    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
    t
    -2.63
    F
    -2.27
    G
    -2.14
    U
    -2.14
     hebben
    -2.09
     queridos
    -2.08
     pivotal
    -2.05
    D
    -1.99
    amp
    -1.98
      
    -1.92
    POSITIVE LOGITS
     که
    2.69
     Они
    2.05
     пробле
    1.91
     που
    1.91
    購入
    1.90
     That
    1.90
    飮
    1.88
    ()]
    1.88
    ":
    1.84
    postmedia
    1.81
    Activations Density 0.090%

    No Known Activations