© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 673
    Prev
    Next
    INDEX
    Explanations

    instructional content or lists

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

    list item markers

    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_53_width_65k_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
    ჯგუფი
    0.31
     stars
    0.30
    :“
    0.30
    ：“
    0.28
     nominations
    0.28
    RELAND
    0.27
    :"
    0.27
     aster
    0.27
     :"
    0.27
    ებაში
    0.27
    POSITIVE LOGITS
    *
    1.20
    <blockquote>
    0.76
     *
    0.62
    ⦁
    0.61
    ●
    0.60
    <ul>
    0.57
    *$
    0.56
    <h3>
    0.55
    <h4>
    0.55
    <h5>
    0.55
    Activations Density 0.362%

    No Known Activations