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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110586
    Prev
    Next
    INDEX
    Explanations

    swan and Swansea

    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
    Šaltiniai
    -0.77
     Aachen
    -0.76
    🛳
    -0.73
    🚢
    -0.71
    AuthProvider
    -0.71
    Pascal
    -0.71
     tendance
    -0.69
     годы
    -0.68
    Dtl
    -0.68
    ╴
    -0.67
    POSITIVE LOGITS
     swan
    4.38
     swans
    4.03
     Swan
    3.91
    Swan
    3.61
    swan
    3.45
     Swans
    3.20
    🦢
    2.36
     Swann
    2.02
     Schwan
    1.89
     Swansea
    1.64
    Activations Density 0.027%

    No Known Activations