© 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-16K
    7. 10625
    Prev
    Next
    INDEX
    Explanations

    common or frequently

    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_16k_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
    Used
    0.73
    Partial
    0.72
     сутки
    0.67
     ধারা
    0.66
     fortnight
    0.64
    ‸
    0.64
     southbound
    0.63
     USED
    0.63
    ബാ
    0.63
     month
    0.62
    POSITIVE LOGITS
     frequently
    2.56
     frequent
    2.48
     Frequent
    2.28
     Frequently
    2.28
    Frequent
    2.20
     fréquemment
    2.16
     häufig
    2.16
     часто
    2.13
    经常
    2.11
    頻
    2.09
    Activations Density 0.344%

    No Known Activations