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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3422
    Prev
    Next
    INDEX
    Explanations

    universe expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    কোত্তর
    0.47
     fréquence
    0.46
     réduite
    0.46
    窄
    0.44
     sách
    0.43
    Narrow
    0.43
     chặt
    0.43
    軛
    0.43
    穩
    0.43
    痪
    0.43
    POSITIVE LOGITS
     expand
    2.09
     expansion
    2.09
     Expansion
    2.03
    Expansion
    1.90
     Expand
    1.89
     expanding
    1.88
     expands
    1.88
    expansion
    1.86
     Expanding
    1.83
    expand
    1.79
    Activations Density 0.007%

    No Known Activations