© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38453
    Prev
    Next
    INDEX
    Explanations

    sports cars and muscle cars

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

    The neuron strongly activates on automotive makes and model designations—particularly car brand names and alphanumeric model codes.

    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
    这家伙
    -1.38
    𝒫
    -1.16
     jengibre
    -1.15
     yayınları
    -1.15
    中です
    -1.13
    回调
    -1.09
     السياس
    -1.09
     acrylique
    -1.08
     informacion
    -1.08
     Insets
    -1.07
    POSITIVE LOGITS
    怔
    1.22
    Fastest
    1.19
     exhilar
    1.17
    izacji
    1.15
     dibandingkan
    1.12
     diseñada
    1.11
     Ведь
    1.09
    皷
    1.08
    かどうか
    1.05
    enangan
    1.05
    Activations Density 0.036%

    No Known Activations