© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76924
    Prev
    Next
    INDEX
    Explanations

    find complex Fourier series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     layouts
    -0.79
    layouts
    -0.76
     genoc
    -0.76
     باقی
    -0.70
     duele
    -0.69
    ɾ
    -0.69
    ixante
    -0.68
     eucalyptus
    -0.68
    畢竟
    -0.67
     yore
    -0.66
    POSITIVE LOGITS
     Fourier
    1.33
    Fourier
    1.15
     periodic
    0.99
    Periodic
    0.97
    周期
    0.92
    periodic
    0.92
     Periodic
    0.90
     fou
    0.86
     Fou
    0.84
     kosme
    0.81
    Activations Density 0.039%

    No Known Activations