© 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. 6483
    Prev
    Next
    INDEX
    Explanations

    questions following technical explanations

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

    first, initial, updated

    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
     править
    0.42
     seaborn
    0.41
    ഃ
    0.41
    ఱ
    0.39
     алге
    0.39
    லம்
    0.39
     zwią
    0.39
     rearrangement
    0.38
     Algebraic
    0.38
    PhysRev
    0.38
    POSITIVE LOGITS
    <code>
    0.48
    custId
    0.44
     palladium
    0.42
    <blockquote>
    0.42
    ---->
    0.42
    ////
    0.41
     //@
    0.40
     //
    0.39
    everyone
    0.39
    dataSource
    0.39
    Activations Density 0.003%

    No Known Activations