© 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. 92268
    Prev
    Next
    INDEX
    Explanations

    alternatives or UI navigation

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

    of length

    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
    cheap
    0.45
    图书
    0.43
    construction
    0.42
     Cheap
    0.42
     احتاج
    0.42
     важней
    0.42
     roughly
    0.39
    fortunately
    0.39
     पुस्तकें
    0.39
    📚
    0.39
    POSITIVE LOGITS
    NavBar
    0.53
     অথবা
    0.49
    NavigationView
    0.46
     లేదా
    0.46
    رز
    0.45
     หรือ
    0.45
     किंवा
    0.45
    又は
    0.43
     alebo
    0.43
     visor
    0.43
    Activations Density 0.000%

    No Known Activations