© 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. 10-GEMMASCOPE-RES-131K
    7. 66671
    Prev
    Next
    INDEX
    Explanations

    city names and districts

    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_10/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
    地在
    -1.91
     what
    -1.80
    This
    -1.76
     not
    -1.70
     spezielle
    -1.70
     Like
    -1.62
     of
    -1.60
     Everything
    -1.59
     только
    -1.59
    ;
    -1.59
    POSITIVE LOGITS
    Famous
    1.65
    无尽
    1.62
    䛗
    1.56
    barten
    1.56
     initializes
    1.56
     vorm
    1.55
     feroit
    1.55
    搋
    1.55
    骉
    1.55
    ㈫
    1.54
    Activations Density 0.008%

    No Known Activations