© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50834
    Prev
    Next
    INDEX
    Explanations

    size, called, specific, there, most, national, memory

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

    academic, religious, training, rebuilding

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     दशकों
    0.50
    四川
    0.49
     décadas
    0.46
     startet
    0.46
    енты
    0.42
    喺
    0.42
     listy
    0.41
    કારે
    0.41
    默默
    0.41
    台灣
    0.41
    POSITIVE LOGITS
    .
    0.49
    .”
    0.47
     a
    0.47
     citizenship
    0.47
    竞争力
    0.46
    。
    0.46
     an
    0.46
     itself
    0.45
    ↵
    0.45
     something
    0.45
    Activations Density 0.000%

    No Known Activations