© 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-262K
    7. 5430
    Prev
    Next
    INDEX
    Explanations

    recursive function

    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
    ्ट
    1.52
    น
    1.52
    ্টার
    1.49
    ભગ
    1.45
    ব
    1.45
    ים
    1.42
    tı
    1.42
    น้อง
    1.40
    ﻕ
    1.33
    ்ப
    1.31
    POSITIVE LOGITS
     وعلى
    1.71
    ‌ی
    1.60
    ما
    1.59
    eta
    1.55
    isten
    1.51
     независимо
    1.40
    И
    1.40
    е
    1.39
    र
    1.38
    ⿷
    1.38
    Activations Density 0.007%

    No Known Activations