© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3704
    Prev
    Next
    INDEX
    Explanations

    the number 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    い
    2.30
    ı
    2.27
    y
    2.20
    i
    2.16
    ح
    2.14
    mmm
    2.11
     Fiesta
    2.11
    ز
    2.11
     Network
    2.06
    t
    2.06
    POSITIVE LOGITS
    ل
    3.05
    氇
    2.91
    нутри
    2.69
    ка
    2.55
    ى
    2.41
    ır
    2.28
    어
    2.19
    ็ม
    2.09
    бліоте
    2.09
    κ
    2.03
    Activations Density 0.215%

    No Known Activations