© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 57051
    Prev
    Next
    INDEX
    Explanations

    Chinese Fishing Nets

    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
    Earl
    0.37
    proxy
    0.37
    ழ
    0.37
    rti
    0.36
    orte
    0.36
    刺激
    0.36
    Generator
    0.35
    Zoom
    0.35
    illiams
    0.34
    harry
    0.34
    POSITIVE LOGITS
     net
    2.83
     nets
    2.41
     Net
    2.25
    net
    2.19
     neto
    2.13
    净
    2.11
     NET
    2.08
     netto
    2.08
     netting
    2.08
    Net
    2.06
    Activations Density 0.004%

    No Known Activations