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. 9-GEMMASCOPE-2-RES-262K
    4. 7876
    Prev
    Next
    INDEX
    Explanations

    scanning for data or systems

    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
    كي
    2.87
    ための
    2.73
    儡
    2.73
     pinnacle
    2.62
    וש
    2.59
    ей
    2.58
    ตู
    2.56
     hati
    2.56
    esse
    2.49
    یز
    2.47
    POSITIVE LOGITS
    ্ট
    3.45
    ا
    3.12
    ne
    3.06
    檛
    2.93
    в
    2.91
    પણે
    2.79
    ए
    2.74
     výraz
    2.74
     ¹
    2.74
    ر
    2.68
    Activations Density 0.020%

    No Known Activations