© 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. 93066
    Prev
    Next
    INDEX
    Explanations

    travel planning 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
     incluidas
    -1.09
            
    -1.03
    Ogre
    -0.91
     incluidos
    -0.90
    диться
    -0.87
    \
    -0.84
     прости
    -0.84
     profundas
    -0.81
     profond
    -0.80
    ում
    -0.79
    POSITIVE LOGITS
     trip
    1.62
    trip
    1.45
     Trip
    1.41
    tych
    1.36
    Trip
    1.25
     planner
    1.24
    wire
    1.19
     tripping
    1.14
     planning
    1.13
     planners
    1.11
    Activations Density 0.009%

    No Known Activations