Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 53081
    Prev
    Next
    INDEX
    Explanations

    prep time

    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_29_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
    MA
    0.72
    ிற்க
    0.68
    sticker
    0.67
    ricks
    0.67
     식
    0.66
    ma
    0.65
    uretic
    0.64
     রাষ্ট্রীয়
    0.64
     touche
    0.64
    কিং
    0.64
    POSITIVE LOGITS
     Boots
    0.65
     quà
    0.65
     Hadid
    0.64
     Glas
    0.63
    জগ
    0.62
     boots
    0.61
    ewell
    0.61
     संक्षिप्त
    0.61
     उपराष्ट्रपति
    0.61
    筵
    0.61
    Activations Density 0.013%

    No Known Activations