© 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. 58603
    Prev
    Next
    INDEX
    Explanations

    geographical regions

    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
     Suomen
    -0.82
     Understanding
    -0.71
    furry
    -0.69
     enamorado
    -0.68
    Suomen
    -0.68
     modernas
    -0.66
     understand
    -0.66
     auxiliar
    -0.66
     síndrome
    -0.65
     understanding
    -0.65
    POSITIVE LOGITS
     region
    2.33
     Region
    2.31
    Region
    2.13
    region
    1.95
    REGION
    1.94
     Regions
    1.92
     regions
    1.88
    regions
    1.70
     REGION
    1.66
     Regionen
    1.64
    Activations Density 0.045%

    No Known Activations