© 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. 59196
    Prev
    Next
    INDEX
    Explanations

    tunnel junctions

    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
    photography
    0.44
     Crystals
    0.41
     Photography
    0.39
     মণ
    0.39
     isotropy
    0.38
    lattice
    0.38
    鿢
    0.38
     كث
    0.38
     ур
    0.38
     تع
    0.37
    POSITIVE LOGITS
     tunnel
    0.88
     tunneling
    0.83
     Tunnel
    0.80
    Tunnel
    0.77
     tunnelling
    0.73
     tunnels
    0.72
    tunnel
    0.71
     conductance
    0.66
    隧道
    0.65
    隧
    0.56
    Activations Density 0.002%

    No Known Activations