© 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. 91668
    Prev
    Next
    INDEX
    Explanations

    under pressure

    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
     luft
    -0.75
     Unterlagen
    -0.74
     рисун
    -0.70
    largest
    -0.69
     McG
    -0.69
     Kash
    -0.69
    large
    -0.68
     Pfa
    -0.68
    ija
    -0.66
    luft
    -0.66
    POSITIVE LOGITS
     pressure
    2.47
     pressures
    2.23
    pressure
    1.92
    Pressure
    1.75
     Pressure
    1.67
     presión
    1.52
    圧
    1.49
     ciś
    1.45
    压力
    1.45
     فشار
    1.45
    Activations Density 0.064%

    No Known Activations