© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1742
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     Особенно
    0.78
     adegu
    0.75
     அளிக்க
    0.74
    t
    0.73
     особенно
    0.73
    oscale
    0.73
     élast
    0.73
     alojamiento
    0.72
    kę
    0.72
    騰
    0.72
    POSITIVE LOGITS
     trận
    0.89
     বিগত
    0.83
     millioner
    0.81
     것이다
    0.79
     प्रतीत
    0.79
    غير
    0.79
     sud
    0.79
    繁
    0.78
     bong
    0.78
    razier
    0.77
    Activations Density 0.397%

    No Known Activations