© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2454
    Prev
    Next
    INDEX
    Explanations

    also known as

    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_22_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
    確実に
    0.78
     اريد
    0.73
     اولا
    0.66
     বিজ্ঞপ্তি
    0.65
    റിൽ
    0.62
    සිය
    0.62
    きちんと
    0.61
     müsste
    0.60
     dürfte
    0.59
    చ్చ
    0.59
    POSITIVE LOGITS
     called
    3.91
    called
    3.54
     termed
    3.45
     Called
    3.35
     llamado
    3.18
    稱為
    3.16
    称为
    3.15
    Called
    3.10
     dubbed
    3.06
     disebut
    3.05
    Activations Density 0.399%

    No Known Activations