© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5199
    Prev
    Next
    INDEX
    Explanations

    roads and travel

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

    transportation networks and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وام
    0.43
    পুর
    0.41
    藉
    0.40
    িকালে
    0.38
    طي
    0.37
    bbero
    0.36
     ЖК
    0.36
    碱
    0.36
     இடம்
    0.36
     مضبوط
    0.36
    POSITIVE LOGITS
     network
    1.05
     networks
    1.05
     नेटवर्क
    1.01
    network
    0.94
    ネットワーク
    0.94
     сеть
    0.92
     NETWORK
    0.91
    networks
    0.91
     сети
    0.89
    网络的
    0.87
    Activations Density 0.104%

    No Known Activations