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. 642
    Prev
    Next
    INDEX
    Explanations

    historical facts and data accuracy

    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
    lə
    0.69
     обеспечивает
    0.65
    mathbf
    0.64
    rfloor
    0.63
     quát
    0.63
    larıyla
    0.63
    㳑
    0.62
    ዐ
    0.62
     می‌کند
    0.62
     détermine
    0.61
    POSITIVE LOGITS
     mafia
    0.84
     mans
    0.83
     pink
    0.82
     인간
    0.82
     sach
    0.80
     abnorm
    0.80
     człowie
    0.79
    vivo
    0.78
     челове
    0.78
     bronchial
    0.76
    Activations Density 0.000%

    No Known Activations