© 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. 109049
    Prev
    Next
    INDEX
    Explanations

    history and British

    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
    蜇
    0.46
     divine
    0.45
    年在
    0.44
    贊
    0.44
    榨
    0.43
    长老
    0.43
    盞
    0.43
     sprinkle
    0.42
    ্নান
    0.42
    ვენ
    0.42
    POSITIVE LOGITS
     ရက်
    0.50
     اسک
    0.48
     رکھے
    0.45
     отдельные
    0.45
    ्या
    0.45
     বিপুল
    0.45
     đón
    0.44
    {~
    0.44
     între
    0.44
     !
    0.43
    Activations Density 0.000%

    No Known Activations