© 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. 62898
    Prev
    Next
    INDEX
    Explanations

    air + Force / vehicle / worthiness

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on aviation-related terms, especially any occurrence of “air” or “flight” in words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    culaire
    -0.83
    oxidant
    -0.76
    astify
    -0.74
    Pvt
    -0.71
    рыв
    -0.70
     Airplane
    -0.70
    ุน
    -0.69
     drone
    -0.69
    ม้
    -0.68
    yf
    -0.68
    POSITIVE LOGITS
    frames
    0.90
    frame
    0.88
    field
    0.86
    crew
    0.84
     launched
    0.80
     unworthy
    0.79
    worthiness
    0.79
    INTER
    0.78
     superiority
    0.75
    fields
    0.74
    Activations Density 0.022%

    No Known Activations