© 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. 192852
    Prev
    Next
    INDEX
    Explanations

    future expectations, largest economy, with access

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

    economic activity

    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
    iense
    0.47
     جميلة
    0.46
     önemlidir
    0.45
    囝
    0.44
     أول
    0.43
     ءِ
    0.43
     ת
    0.42
    彥
    0.42
     första
    0.42
     tugas
    0.42
    POSITIVE LOGITS
    ỡng
    0.43
    ಲೂ
    0.40
    awar
    0.39
    存在
    0.39
     migr
    0.39
     molest
    0.38
    uct
    0.38
     secretions
    0.37
     exist
    0.37
     ойной
    0.37
    Activations Density 0.000%

    No Known Activations