© 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. 139426
    Prev
    Next
    INDEX
    Explanations

    optimization and systems

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

    Edward playing, less fatigue, constant checking

    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
     horseradish
    0.43
     ခ
    0.42
    iget
    0.42
    alá
    0.42
    asi
    0.41
     ঈ
    0.41
    gó
    0.41
     contractions
    0.41
     depressions
    0.41
    jin
    0.40
    POSITIVE LOGITS
     وصل
    0.51
     plastique
    0.51
    رید
    0.50
    मोरी
    0.50
     partie
    0.50
     plast
    0.47
    ي
    0.47
    ווי
    0.46
     ارائه
    0.46
    uriken
    0.46
    Activations Density 0.001%

    No Known Activations