© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91245
    Prev
    Next
    INDEX
    Explanations

    detachable street

    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
     computer
    -1.26
     acrylic
    -1.20
    computer
    -1.14
     laser
    -1.05
     Computer
    -1.04
     PowerPoint
    -1.04
     Bluetooth
    -1.02
    laser
    -1.02
     SUV
    -1.02
     Laser
    -1.00
    POSITIVE LOGITS
     kerosene
    1.00
     telegraph
    1.00
     Pyrene
    0.97
     acety
    0.96
     paraffin
    0.95
     breadcrumbs
    0.93
     battled
    0.89
     telegram
    0.87
     AKT
    0.85
     turkish
    0.85
    Activations Density 0.051%

    No Known Activations