© 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. 53-GEMMASCOPE-2-RES-65K
    4. 2243
    Prev
    Next
    INDEX
    Explanations

    N followed by specific endings

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

    NVIDIA, nihil, surnames

    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
    ीय
    0.69
    률
    0.66
    로부터
    0.54
    дің
    0.54
    ிருக்கிறார்
    0.52
    로운
    0.52
    دخل
    0.50
    ⅼ
    0.49
    ИТ
    0.48
     অবলম্বন
    0.48
    POSITIVE LOGITS
    atural
    1.13
    uclear
    1.09
    netje
    1.07
    ormal
    1.05
    vironment
    1.04
    autical
    1.04
    ascimento
    1.02
    utrients
    1.01
    ouncement
    1.00
    aughty
    0.99
    Activations Density 0.919%

    No Known Activations