© 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
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 15204
    Prev
    Next
    INDEX
    Explanations

    server related phrases

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

    fundamental forces and equations

    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_16_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
    atributo
    0.49
    אים
    0.47
    い
    0.47
    ്രാ
    0.47
    ISTICS
    0.46
    یت
    0.46
     dropping
    0.46
    GLAND
    0.46
    嚨
    0.45
    か
    0.45
    POSITIVE LOGITS
    list
    0.51
     फोर
    0.50
     keys
    0.47
     [
    0.47
    seed
    0.47
    news
    0.46
    Fore
    0.46
    বাস
    0.44
    print
    0.44
    ayog
    0.44
    Activations Density 0.004%

    No Known Activations