© 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. 8652
    Prev
    Next
    INDEX
    Explanations

    Mr followed by name or title

    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
    了一个
    1.61
    في
    1.52
     čet
    1.50
    Под
    1.46
    一個
    1.46
    А
    1.43
     dodging
    1.42
    了一個
    1.42
     Gelände
    1.42
     écl
    1.42
    POSITIVE LOGITS
    挝
    2.02
    们的
    1.73
     orifice
    1.61
    róleo
    1.55
    naio
    1.50
    ordinating
    1.49
     oath
    1.47
     anointed
    1.46
    ણા
    1.45
    们
    1.45
    Activations Density 0.031%

    No Known Activations