© 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. 53-GEMMASCOPE-2-RES-65K
    7. 8626
    Prev
    Next
    INDEX
    Explanations

    British Columbia, yoga mat, alma mater, make matters

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

    mat or Matura

    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_53_width_65k_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
    霹
    0.33
    DSA
    0.33
    ThreadGroup
    0.33
    едера
    0.32
    вли
    0.32
    hkse
    0.32
    悛
    0.32
    梗
    0.31
     Frege
    0.31
    BURSE
    0.31
    POSITIVE LOGITS
     mat
    4.09
    Mat
    4.00
     MAT
    3.94
     Mat
    3.91
    mat
    3.86
    MAT
    3.81
     Мат
    3.39
     mats
    3.36
     мат
    3.33
     Mathew
    3.33
    Activations Density 0.302%

    No Known Activations