© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104741
    Prev
    Next
    INDEX
    Explanations

    List of items or layouts

    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_22/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
    iembre
    -0.98
     to
    -0.94
    peka
    -0.87
    病情
    -0.86
     &___
    -0.86
    ia
    -0.85
    grees
    -0.83
    nake
    -0.83
    PasswordEncoder
    -0.82
    yafet
    -0.82
    POSITIVE LOGITS
    巯
    1.02
    cú
    1.01
    onekana
    0.98
    ulisan
    0.98
     toimi
    0.96
    参考にして
    0.93
    ₥
    0.93
    Ѐ
    0.92
     באופן
    0.92
     Trou
    0.91
    Activations Density 0.002%

    No Known Activations