© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76005
    Prev
    Next
    INDEX
    Explanations

    aerospace and aviation vocabulary

    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
     Tomar
    -0.84
     wieś
    -0.77
     Lowry
    -0.76
     decid
    -0.74
    极限
    -0.74
    niejsza
    -0.73
     kör
    -0.73
     lament
    -0.72
     affront
    -0.72
     Ito
    -0.72
    POSITIVE LOGITS
     winds
    0.84
     Verlet
    0.83
     waypoint
    0.82
     intersection
    0.78
     transition
    0.78
     assigned
    0.78
     intersections
    0.78
     Climb
    0.78
     ECON
    0.77
     termination
    0.76
    Activations Density 0.018%

    No Known Activations