© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    're and 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     উল্লেখযোগ্য
    0.64
     monograph
    0.63
    FileAlignment
    0.62
    ర్జ
    0.61
    собенности
    0.58
     culminates
    0.56
     ו
    0.56
    вов
    0.55
     específica
    0.55
     הספר
    0.55
    POSITIVE LOGITS
     Thank
    1.06
     Thanks
    1.05
    Thank
    1.03
     Didn
    0.99
     :)
    0.99
    thank
    0.98
     спасибо
    0.97
     Alright
    0.97
     Sorry
    0.95
    那我
    0.95
    Activations Density 0.250%

    No Known Activations