© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77706
    Prev
    Next
    INDEX
    Explanations

    networking equipment and connections

    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
    سى
    -0.76
     Microb
    -0.75
     Presidential
    -0.75
     SERVICES
    -0.75
     ر
    -0.70
    OMET
    -0.69
     аккумулятор
    -0.68
     Break
    -0.67
    breakpoint
    -0.67
     lửa
    -0.66
    POSITIVE LOGITS
     plugs
    1.17
    Plug
    1.13
     plug
    1.06
     Plug
    1.06
    plug
    0.85
     plugged
    0.84
     Rollo
    0.83
    PLC
    0.82
     PLC
    0.81
    ineas
    0.81
    Activations Density 0.031%

    No Known Activations