© 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. 63508
    Prev
    Next
    INDEX
    Explanations

    gasoline pumps and stations

    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
    lož
    -0.86
    Boiler
    -0.82
    QColor
    -0.81
     cAMP
    -0.77
    carrito
    -0.77
    cadastro
    -0.77
     postman
    -0.77
    ISM
    -0.76
    steam
    -0.75
     medži
    -0.74
    POSITIVE LOGITS
     pumps
    1.63
     pump
    1.52
    pump
    1.32
     Pump
    1.28
     nozzle
    1.23
    Pump
    1.21
     attendants
    1.21
     stations
    1.20
     nozzles
    1.19
     Pumps
    1.18
    Activations Density 0.015%

    No Known Activations