© 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. 14468
    Prev
    Next
    INDEX
    Explanations

    future ready

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

    private keytriumph when

    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
    枒
    0.40
    叵
    0.39
    狞
    0.38
     বেশি
    0.36
     ভালোবাসি
    0.36
     ট্রেন
    0.35
     fluff
    0.34
     oud
    0.34
    defines
    0.34
     قل
    0.34
    POSITIVE LOGITS
    ithmetic
    0.42
     comprehend
    0.36
    ﭥ
    0.35
     progressed
    0.35
     Бен
    0.35
     Ра
    0.33
     шан
    0.33
    placeholder
    0.33
     непотпу
    0.33
     જી
    0.33
    Activations Density 0.001%

    No Known Activations