© 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. 11797
    Prev
    Next
    INDEX
    Explanations

    first league results

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

    Fourier transform and frequency domain

    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
    <unused47>
    0.44
    Puedes
    0.43
     kennt
    0.42
    bss
    0.40
    殑
    0.39
    bestroute
    0.39
     fác
    0.39
    kö
    0.38
     عنه
    0.38
     constantemente
    0.38
    POSITIVE LOGITS
     ,
    0.61
     transform
    0.57
     line
    0.53
     lines
    0.52
    transform
    0.49
     Lines
    0.48
     cross
    0.47
     mad
    0.47
     matrix
    0.46
     fire
    0.46
    Activations Density 0.041%

    No Known Activations