© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13979
    Prev
    Next
    INDEX
    Explanations

    regularity and frequency

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

    regular or frequent events

    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_31_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
    ется
    0.61
     når
    0.59
     keď
    0.59
    每次
    0.57
    ม
    0.57
     mindig
    0.56
    {
    0.55
     an
    0.54
     завжди
    0.54
     aina
    0.53
    POSITIVE LOGITS
    regular
    0.92
     regolare
    0.72
     regularity
    0.70
     रेग
    0.70
    Regular
    0.66
     регуляр
    0.65
     regulares
    0.64
    updates
    0.64
    봤
    0.64
     नियमित
    0.63
    Activations Density 0.371%

    No Known Activations