© 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. 902
    Prev
    Next
    INDEX
    Explanations

    seeing something emerge

    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
     bulunur
    0.51
     найден
    0.48
     determines
    0.48
     เพื่อ
    0.48
    ẃ
    0.47
    FOUND
    0.47
     biedt
    0.47
     trouvent
    0.46
    found
    0.46
    ុង
    0.45
    POSITIVE LOGITS
     firsthand
    0.89
     unfold
    0.75
     👀
    0.66
     увидеть
    0.60
    👀
    0.59
     happen
    0.58
     glimpse
    0.54
     emerge
    0.54
     unfolding
    0.52
     apparaître
    0.52
    Activations Density 0.005%

    No Known Activations