© 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. 116192
    Prev
    Next
    INDEX
    Explanations

    lakes and wilderness

    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
     Salinas
    -0.96
     farmers
    -0.95
    FARM
    -0.94
     farmer
    -0.93
    オーストラリア
    -0.88
     Farmers
    -0.88
     Monterey
    -0.88
    farmers
    -0.87
    Farmers
    -0.85
     Ammon
    -0.81
    POSITIVE LOGITS
     canoe
    1.41
     lake
    1.41
     lakes
    1.27
     canoes
    1.14
     moose
    1.10
     wilderness
    1.09
    cano
    1.08
     loon
    1.05
     Lake
    1.05
     mosquitoes
    1.01
    Activations Density 0.021%

    No Known Activations