© 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. 117837
    Prev
    Next
    INDEX
    Explanations

    journeys and trips

    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
    țională
    -0.78
    läufer
    -0.77
     ซ
    -0.77
    rnn
    -0.76
    iciado
    -0.76
    Év
    -0.75
     тебя
    -0.75
    tahui
    -0.75
    빠
    -0.74
    醣
    -0.71
    POSITIVE LOGITS
     journey
    5.53
     trip
    4.19
    journey
    3.86
     journeys
    3.83
     voyage
    3.67
     Journey
    3.50
     viaje
    3.45
    Journey
    3.33
     viaggio
    3.03
     viagem
    3.00
    Activations Density 0.058%

    No Known Activations