© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11804
    Prev
    Next
    INDEX
    Explanations

    moon, lunar, phases, light

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

    moon and lunar concepts

    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_40_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
    尌
    0.44
    RAF
    0.43
     झांसी
    0.40
    劍
    0.40
     કરતાં
    0.39
    barrier
    0.39
    ើស
    0.39
    ⇄
    0.39
     दै
    0.38
    Bott
    0.38
    POSITIVE LOGITS
     moon
    2.13
     lunar
    2.13
     Moon
    1.96
     Lunar
    1.96
    Lunar
    1.91
    Moon
    1.88
    moon
    1.85
     Luna
    1.79
     luna
    1.74
     moonlight
    1.70
    Activations Density 0.108%

    No Known Activations