© 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. 70274
    Prev
    Next
    INDEX
    Explanations

    Flight Simulator or questions

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

    This neuron detects mentions of flight‐simulation jargon and proper names—especially “Flight Simulator,” “flight dynamics,” “AVSIM,” and related technical terms.

    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
     competencies
    -0.76
     encuentras
    -0.71
    Fatalf
    -0.71
     Ability
    -0.70
     blossom
    -0.70
     Ü
    -0.70
    retan
    -0.69
     encantó
    -0.68
     tournament
    -0.68
     gossip
    -0.68
    POSITIVE LOGITS
    Fs
    0.97
     Fs
    0.88
    Cambio
    0.85
     vectra
    0.82
     FS
    0.82
    ficheiro
    0.82
    ナン
    0.81
    FS
    0.80
     fabia
    0.79
     McP
    0.79
    Activations Density 0.026%

    No Known Activations