© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5789
    Prev
    Next
    INDEX
    Explanations

    interplanetary terrestrial planet

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

    Sir Quackington

    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
     CHECK
    0.42
    EXCEPTION
    0.42
     LENGTH
    0.40
    وینت
    0.40
     пожи
    0.40
    CHECK
    0.39
    LENGTH
    0.37
    待
    0.37
    జ్ఞ
    0.37
     REPORT
    0.36
    POSITIVE LOGITS
     interplanetary
    0.50
     지구
    0.48
    restrial
    0.48
    NASA
    0.47
     planet
    0.46
     Plasma
    0.46
    Plasma
    0.46
    地球
    0.45
     floods
    0.44
     Earth
    0.44
    Activations Density 0.000%

    No Known Activations