© 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. 178531
    Prev
    Next
    INDEX
    Explanations

    categories in listings

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

    phases, terminal, struggles, count

    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
    i
    0.51
     i
    0.49
     INS
    0.47
     compatibles
    0.46
    -​
    0.46
     unten
    0.45
     blueberries
    0.44
    са
    0.43
     MIN
    0.42
     encapsulate
    0.42
    POSITIVE LOGITS
    捨て
    0.57
    わかり
    0.53
     ہاتھ
    0.49
    謂
    0.49
    引き
    0.48
     comunità
    0.48
    cimento
    0.47
     جایی
    0.46
    ോഗ്യ
    0.45
    範圍
    0.45
    Activations Density 0.000%

    No Known Activations