© 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. 64254
    Prev
    Next
    INDEX
    Explanations

    Swedish people and places

    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
     Norwegian
    -0.92
     Stats
    -0.91
     Norway
    -0.84
     Oslo
    -0.82
     fjord
    -0.80
    Olu
    -0.79
     Kompetenz
    -0.78
     Dinamarca
    -0.77
     stave
    -0.77
    Stats
    -0.75
    POSITIVE LOGITS
     svensk
    1.13
     klubben
    1.09
     natten
    1.02
     årets
    0.94
     torsdag
    0.94
     Swedish
    0.91
     fredag
    0.91
     Sverige
    0.87
     vårt
    0.85
     gård
    0.84
    Activations Density 0.041%

    No Known Activations