© 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. 210240
    Prev
    Next
    INDEX
    Explanations

    unique process

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

    natural and technical terms

    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
    ρκ
    0.51
    சொ
    0.50
     getc
    0.49
    को
    0.47
    쵸
    0.47
    설
    0.45
    ன்
    0.44
    سری
    0.44
    이
    0.44
    찍
    0.43
    POSITIVE LOGITS
    RegisterClass
    0.55
    िए
    0.49
     بعض
    0.48
     स्वाभाविक
    0.48
    েনা
    0.48
    अलग
    0.47
    apa
    0.46
     بناء
    0.46
     قاعدة
    0.46
     Comunidad
    0.45
    Activations Density 0.002%

    No Known Activations