© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33612
    Prev
    Next
    INDEX
    Explanations

    locations and fantasy worlds

    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
     German
    -0.73
     Iraqi
    -0.73
     Royal
    -0.69
     město
    -0.69
    司马
    -0.69
     city
    -0.69
     Miami
    -0.68
     Brazilian
    -0.68
     deutscher
    -0.68
    Apis
    -0.68
    POSITIVE LOGITS
    Pang
    1.12
     Pang
    1.04
    æa
    0.94
     Dunia
    0.93
     Gaia
    0.93
     continent
    0.86
     艾
    0.85
    uland
    0.82
    isor
    0.82
    Terra
    0.82
    Activations Density 0.041%

    No Known Activations