© 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. 47545
    Prev
    Next
    INDEX
    Explanations

    simulate sending keys

    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
     electrified
    -0.81
    面積
    -0.73
     enabled
    -0.71
    首都
    -0.67
     binds
    -0.67
     astute
    -0.66
    統計
    -0.65
    Ask
    -0.65
    handeling
    -0.63
    面
    -0.63
    POSITIVE LOGITS
     simulated
    1.13
    simulator
    1.13
    模拟
    1.08
     simulating
    1.02
     simulate
    1.02
     模拟
    1.00
    simulation
    0.99
     simulates
    0.92
    Simulator
    0.92
    Simulation
    0.90
    Activations Density 0.019%

    No Known Activations