© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 9084
    Prev
    Next
    INDEX
    Explanations

    in the style of

    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_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
    ﺍ
    1.54
     Эти
    1.52
    ুল
    1.45
    ுங்கள்
    1.45
    šet
    1.45
    OVA
    1.45
    ৬৫
    1.41
    üle
    1.41
    ૩
    1.41
    AYA
    1.40
    POSITIVE LOGITS
    neſs
    1.48
     agir
    1.45
     exigir
    1.41
    ן
    1.41
     usar
    1.34
     utu
    1.29
     activar
    1.28
     bruto
    1.27
    o
    1.26
     огромное
    1.25
    Activations Density 0.001%

    No Known Activations