© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2751
    Prev
    Next
    INDEX
    Explanations

    quoting or listing files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
     blade
    0.65
     Blade
    0.63
     flood
    0.62
     ሜ
    0.61
     blades
    0.60
    入侵
    0.60
    blade
    0.59
     descon
    0.59
     Blades
    0.59
     FL
    0.58
    POSITIVE LOGITS
    εργ
    0.62
    ureen
    0.62
    넷
    0.62
     প্রকৃতির
    0.61
    QUI
    0.60
    ܩ
    0.58
    বদ্ধ
    0.58
     বিগ
    0.57
    QT
    0.57
    स्ताना
    0.56
    Activations Density 0.158%

    No Known Activations