© 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. 34-GEMMASCOPE-RES-131K
    7. 3013
    Prev
    Next
    INDEX
    Explanations

    Guyana, Trinidad, Suriname names

    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
    
    -0.79
     permainan
    -0.76
    quants
    -0.76
     calorimeter
    -0.74
     Blatt
    -0.74
     Pouch
    -0.73
     بندی
    -0.73
    declare
    -0.73
     phí
    -0.72
    PMC
    -0.72
    POSITIVE LOGITS
     Guyana
    0.84
     Trinidad
    0.84
     Suriname
    0.83
     pensare
    0.82
    Segoe
    0.81
    Guyana
    0.78
    授權
    0.76
    ansing
    0.75
    arine
    0.75
     Outdoors
    0.74
    Activations Density 0.019%

    No Known Activations