© 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. 48474
    Prev
    Next
    INDEX
    Explanations

    barn and outbuildings

    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
    Abstracts
    -0.86
    Jard
    -0.84
     garden
    -0.73
     buta
    -0.73
     scaler
    -0.73
    сная
    -0.73
    logging
    -0.73
    racuda
    -0.72
    sack
    -0.72
    Balancing
    -0.71
    POSITIVE LOGITS
     barn
    2.06
     garage
    1.63
     shed
    1.62
     hangar
    1.61
     warehouse
    1.57
     barns
    1.50
     Barn
    1.40
     sheds
    1.39
     garages
    1.38
     workshop
    1.38
    Activations Density 0.024%

    No Known Activations