© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14462
    Prev
    Next
    INDEX
    Explanations

    XML/HTML opening tags

    np_acts-logits-general · gemini-2.5-flash-lite

    xml document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rück
    0.52
     postérieurs
    0.51
    㶱
    0.51
     суть
    0.46
    䤚
    0.46
    荲
    0.44
     അധ
    0.44
     abhis
    0.44
    皁
    0.43
     asum
    0.43
    POSITIVE LOGITS
    cv
    0.47
    <table>
    0.45
    ο
    0.44
    beautiful
    0.42
    cnf
    0.42
    device
    0.42
    Personnel
    0.41
    xf
    0.41
    Aqua
    0.40
    Information
    0.39
    Activations Density 0.000%

    No Known Activations