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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 52873
    Prev
    Next
    INDEX
    Explanations

    To help me tailor

    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
    DWORD
    0.73
     Deadline
    0.69
     ಕಿ
    0.66
    Ah
    0.65
    Announcement
    0.63
    SDLCheck
    0.63
    原型
    0.63
     ஜ
    0.62
    Recommendations
    0.62
     त्रिपाठी
    0.62
    POSITIVE LOGITS
     夕
    0.83
    mán
    0.79
     ჩ
    0.70
    ificant
    0.68
     تجهیز
    0.67
    تاب
    0.65
     ongoing
    0.65
    uture
    0.65
     buch
    0.64
     Busca
    0.64
    Activations Density 0.013%

    No Known Activations