© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10652
    Prev
    Next
    INDEX
    Explanations

    sampling process optimization

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

    spatial domain and frequency

    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
     nhiễm
    0.43
     মুর
    0.41
     Kob
    0.41
    酱
    0.41
    sender
    0.40
    管理者
    0.40
     염
    0.40
    色素
    0.40
    merk
    0.39
     disequ
    0.39
    POSITIVE LOGITS
     Fourier
    1.35
    Fourier
    1.30
     FFT
    0.97
    convolution
    0.96
     Convolution
    0.93
    fft
    0.92
     convolution
    0.91
     wavelet
    0.91
    Convolution
    0.87
     fft
    0.86
    Activations Density 0.067%

    No Known Activations