© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9524
    Prev
    Next
    INDEX
    Explanations

    end-of-turn text

    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_9_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
    ஸ்
    0.82
    এখন
    0.78
    republik
    0.77
     بعد
    0.77
    Dengan
    0.76
    ди
    0.75
    া
    0.73
    ーーーー
    0.72
     kuning
    0.72
    鈾
    0.72
    POSITIVE LOGITS
    ➢
    0.74
     functors
    0.67
    𝖊
    0.62
     फैली
    0.62
     ingrained
    0.62
     внед
    0.61
    0
    0.61
     rethinking
    0.60
    2
    0.60
     coexist
    0.60
    Activations Density 0.515%

    No Known Activations