© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77530
    Prev
    Next
    INDEX
    Explanations

    uncoupling or disconnecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zcan
    -0.73
    bukaan
    -0.70
    textnormal
    -0.68
     zake
    -0.68
    warna
    -0.66
    zea
    -0.66
    Ẫ
    -0.66
    の見
    -0.65
     Пар
    -0.65
     navigable
    -0.65
    POSITIVE LOGITS
     unplug
    4.22
     unplugged
    3.98
     disconnect
    2.86
     un
    2.64
     disconnected
    2.64
    Un
    2.58
     disconnecting
    2.55
     Un
    2.53
     Disconnect
    2.47
    Disconnect
    2.33
    Activations Density 0.049%

    No Known Activations