© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98993
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    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
     gold
    -0.75
     begon
    -0.75
    φυ
    -0.74
    连接
    -0.73
    Pham
    -0.73
    ácie
    -0.72
    Leopold
    -0.72
     kesk
    -0.71
    trecht
    -0.71
    rentiel
    -0.71
    POSITIVE LOGITS
     Marseille
    0.99
     Tacoma
    0.87
     Harbor
    0.80
    逗
    0.77
    Pred
    0.77
    Harbor
    0.76
     Chadwick
    0.74
    رف
    0.74
     Wilmington
    0.73
    Marseille
    0.73
    Activations Density 0.017%

    No Known Activations