© 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. 10-GEMMASCOPE-RES-131K
    7. 48465
    Prev
    Next
    INDEX
    Explanations

    HMS ship names

    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
     bezw
    -3.42
    鵙
    -3.36
    蟶
    -3.23
    亖
    -3.11
    ᛬
    -3.09
     ſever
    -3.00
    嗩
    -2.97
     ſta
    -2.97
    ⢅
    -2.94
    聼
    -2.91
    POSITIVE LOGITS
    ’
    3.47
    t
    3.22
    man
    3.06
     Throughout
    2.95
     After
    2.86
    when
    2.83
    This
    2.72
    瑧
    2.72
    ….
    2.70
    c
    2.70
    Activations Density 0.009%

    No Known Activations