© 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. 3000
    Prev
    Next
    INDEX
    Explanations

    American and British geography

    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
    Ứng
    -0.74
     proverbial
    -0.71
    门
    -0.70
    ␮
    -0.70
    Toast
    -0.69
    rotter
    -0.68
    Rot
    -0.67
    Ref
    -0.66
    乱
    -0.66
     Ref
    -0.65
    POSITIVE LOGITS
     British
    1.35
     American
    1.30
    British
    1.28
    American
    1.23
     американ
    1.23
     UK
    1.20
     american
    1.15
    AMERICAN
    1.13
     amerikan
    1.06
     AMERICAN
    1.05
    Activations Density 0.038%

    No Known Activations