© 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. 20923
    Prev
    Next
    INDEX
    Explanations

    geographical basins

    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
     ใน
    -3.03
    軚
    -2.59
    俢
    -2.58
    𝓙
    -2.58
    雠
    -2.56
    餿
    -2.53
    艄
    -2.50
     GOtt
    -2.48
     zoude
    -2.45
    鲧
    -2.41
    POSITIVE LOGITS
    <bos>
    3.02
     exquisitely
    2.69
     ingenious
    2.58
     burgeoning
    2.58
    Both
    2.56
     sehr
    2.53
     unwavering
    2.52
    ዡ
    2.48
    鸰
    2.48
     noteworthy
    2.45
    Activations Density 0.007%

    No Known Activations