© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 31
    Prev
    Next
    INDEX
    Explanations

    silence and sound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    не
    0.78
    at
    0.72
    ol
    0.66
    a
    0.66
     І
    0.64
    elun
    0.63
    য়ার
    0.62
     Ее
    0.62
     Perché
    0.61
    esimo
    0.61
    POSITIVE LOGITS
    🎵
    1.08
     песни
    0.96
    歌曲
    0.93
     музыки
    0.92
    เพลง
    0.91
     музыку
    0.88
    🎼
    0.85
     musik
    0.84
     muzy
    0.84
     nhạc
    0.83
    Activations Density 1.476%

    No Known Activations