© 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. 92067
    Prev
    Next
    INDEX
    Explanations

    Captain mistakes leading to disasters

    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
     Heidegger
    -0.90
    機場
    -0.90
     červen
    -0.84
    اشة
    -0.82
     hostage
    -0.81
    Heidelberg
    -0.80
    kär
    -0.78
    ponenten
    -0.77
     helicopter
    -0.75
    deles
    -0.75
    POSITIVE LOGITS
     Titanic
    2.09
    Titanic
    1.67
     iceberg
    1.24
     RMS
    1.22
     passengers
    1.07
     пассажи
    1.01
    titanic
    1.01
     pasajeros
    1.01
     Southampton
    0.99
    RMS
    0.99
    Activations Density 0.009%

    No Known Activations