© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 174404
    Prev
    Next
    INDEX
    Explanations

    Commodore, mistake, signs, offended, video, Partridge, term

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

    divorce, strategy, vacuuming, analysis, outline, protects

    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_262k_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
     enz
    0.51
     odre
    0.46
     saud
    0.45
     społ
    0.45
     nota
    0.45
     ,'
    0.44
     objc
    0.44
    妹
    0.44
    肱
    0.44
     ezért
    0.43
    POSITIVE LOGITS
    ’
    0.47
    门口
    0.46
     कार्यक्रमों
    0.46
    हरे
    0.44
     मंडळा
    0.44
     coordinators
    0.44
    ी
    0.44
    icycles
    0.43
    agnar
    0.43
    uing
    0.42
    Activations Density 0.001%

    No Known Activations