© 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. 77945
    Prev
    Next
    INDEX
    Explanations

    pilot, jets

    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
    áb
    -0.79
     žen
    -0.77
    EditMode
    -0.73
     Henn
    -0.71
    慈
    -0.69
    xfb
    -0.69
    RAINT
    -0.69
    ريد
    -0.69
     created
    -0.68
    んな
    -0.66
    POSITIVE LOGITS
     jets
    1.59
     jet
    1.40
     Jets
    1.38
     needle
    1.21
     Jet
    1.16
    jet
    1.12
    Jets
    1.09
    ジェット
    1.07
     Pilot
    0.99
     pilot
    0.98
    Activations Density 0.004%

    No Known Activations