© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 44113
    Prev
    Next
    INDEX
    Explanations

    multilingual words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    ing
    0.73
    i
    0.68
    ي
    0.64
    t
    0.62
    n
    0.60
    u
    0.55
    rite
    0.55
    k
    0.55
    ny
    0.54
    ex
    0.51
    POSITIVE LOGITS
     būt
    0.54
     LOTRAchievement
    0.52
     sonuç
    0.52
     revêt
    0.52
     সর্বো
    0.50
     sĩ
    0.48
     lihat
    0.48
     ไม่มี
    0.48
     kişi
    0.48
    ᶜ
    0.48
    Activations Density 0.000%

    No Known Activations