© 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. 31853
    Prev
    Next
    INDEX
    Explanations

    CRT monitor tube

    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
     cheese
    -0.83
     hive
    -0.77
     Tami
    -0.73
    baya
    -0.72
     cloud
    -0.72
    CLOUD
    -0.71
     salvajes
    -0.71
     voice
    -0.71
    getClassName
    -0.70
     USB
    -0.70
    POSITIVE LOGITS
     crt
    1.10
     tube
    1.08
     CRT
    1.06
     Trinit
    1.05
    tube
    1.01
     phosph
    1.00
     deflection
    0.92
     TUBE
    0.87
    phosph
    0.85
    CRT
    0.83
    Activations Density 0.065%

    No Known Activations