© 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. 22-GEMMASCOPE-RES-131K
    7. 65143
    Prev
    Next
    INDEX
    Explanations

    inspired by past styles and eras

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

    The neuron detects references to classic or vintage aviation–inspired design elements (e.g. “classic airplane cockpits,” “analog”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     nuevos
    -1.26
    着一个
    -1.17
    了一会儿
    -1.17
    姦
    -1.07
     or
    -1.05
    tholes
    -1.04
    ifique
    -1.03
     neuen
    -1.03
    tifiable
    -1.03
    icamente
    -1.01
    POSITIVE LOGITS
     of
    1.28
     namun
    1.08
    boda
    1.01
     lenne
    0.97
     chré
    0.96
    zmm
    0.96
    ׇ
    0.93
     saveurs
    0.93
     tunt
    0.93
     természetes
    0.92
    Activations Density 0.058%

    No Known Activations