© 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. 9607
    Prev
    Next
    INDEX
    Explanations

    columns in tables

    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
    ıdır
    1.76
     avut
    1.72
     რამდ
    1.67
     რომელი
    1.62
    ရား
    1.55
    ▣
    1.55
     monday
    1.53
    娩
    1.52
     لیگ
    1.51
    $('.
    1.51
    POSITIVE LOGITS
    ع
    2.12
    ন্ত
    1.79
    in
    1.58
    s
    1.57
    യുടെ
    1.51
    গুলি
    1.49
    marginTop
    1.48
    dataLayer
    1.47
     appendage
    1.46
    at
    1.45
    Activations Density 0.006%

    No Known Activations