© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13979
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {
    0.75
     {
    0.55
    ม
    0.55
     første
    0.55
    ร
    0.54
     caz
    0.54
     an
    0.51
     first
    0.51
     initially
    0.50
     fingert
    0.50
    POSITIVE LOGITS
    regular
    0.86
    Regular
    0.64
    z
    0.63
     regolare
    0.61
     regular
    0.60
     регуляр
    0.56
     regulares
    0.56
     Updates
    0.55
     regularity
    0.55
    alities
    0.55
    Activations Density 0.179%

    No Known Activations