© 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. 64745
    Prev
    Next
    INDEX
    Explanations

    coupled connections

    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
     дож
    0.40
     आईडी
    0.40
    ंगा
    0.39
     Jehová
    0.39
    কন
    0.38
    𝙀
    0.38
    ify
    0.37
    猛
    0.37
     плю
    0.37
    节奏
    0.36
    POSITIVE LOGITS
     connected
    0.74
     connection
    0.74
     conectados
    0.66
     conectado
    0.65
     operable
    0.64
     removable
    0.63
     detachable
    0.62
     Connected
    0.61
    connected
    0.61
    Connected
    0.61
    Activations Density 0.002%

    No Known Activations