© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1501
    Prev
    Next
    INDEX
    Explanations

    common phrases and multilingual characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     study
    0.69
     следующем
    0.66
     следующее
    0.62
     Study
    0.60
     स्टडी
    0.60
    泷
    0.60
    同比
    0.60
    郯
    0.59
     다음
    0.59
     retain
    0.59
    POSITIVE LOGITS
    ცხ
    0.67
     writeFile
    0.62
    רו
    0.58
    分の
    0.58
    ξη
    0.57
     குடிய
    0.56
    ചി
    0.56
    ুন
    0.55
    шей
    0.55
    ایط
    0.54
    Activations Density 0.455%

    No Known Activations