© 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. 104022
    Prev
    Next
    INDEX
    Explanations

    Whoa. Woah

    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
     ก็
    -1.77
    when
    -1.75
    м
    -1.72
     した
    -1.65
    -
    -1.62
    マジ
    -1.62
     Và
    -1.61
    ه
    -1.61
     WHEN
    -1.60
    b
    -1.59
    POSITIVE LOGITS
    のご紹介
    2.02
    洐
    1.80
    ☫
    1.80
    の紹介
    1.66
    ilers
    1.66
    大半
    1.65
    磧
    1.63
    我也是
    1.62
     are
    1.60
    namics
    1.60
    Activations Density 0.002%

    No Known Activations