© 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. 8833
    Prev
    Next
    INDEX
    Explanations

    Error Handling

    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
    𝑛
    3.72
    ことにより
    3.66
    ان
    3.28
    𝑙
    3.09
    𝑖
    2.99
    ことです
    2.91
    𝑠
    2.88
    𝑟
    2.85
    𝑑
    2.82
    𝐼
    2.78
    POSITIVE LOGITS
    ер
    3.28
     deem
    2.44
    উল্লেখ্য
    2.38
     schließlich
    2.37
    ть
    2.36
     excuses
    2.32
     esperado
    2.23
     incandescent
    2.19
     youngest
    2.18
     obscene
    2.16
    Activations Density 0.020%

    No Known Activations