© 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. 2796
    Prev
    Next
    INDEX
    Explanations

    aircraft landing gear

    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
     roadside
    -0.87
    along
    -0.87
    沿
    -0.81
     along
    -0.80
     Along
    -0.78
    biol
    -0.77
     вдоль
    -0.76
    Along
    -0.75
     alongside
    -0.75
    Alongside
    -0.75
    POSITIVE LOGITS
     wheels
    1.35
     retract
    1.26
     landing
    1.23
     retraction
    1.20
     gear
    1.19
     Wheels
    1.17
     wheel
    1.16
     struts
    1.08
     strut
    1.08
     Ret
    1.08
    Activations Density 0.023%

    No Known Activations