© 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. 205833
    Prev
    Next
    INDEX
    Explanations

    debt consolidation loans

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

    towards general intelligence

    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
    ذي
    0.45
     viejo
    0.45
    ISING
    0.43
    ву
    0.42
    אל
    0.42
    饮
    0.41
    Hochspringen
    0.41
     NONINFRINGEMENT
    0.40
    临
    0.40
     malad
    0.40
    POSITIVE LOGITS
     الأطفال
    0.55
     എന്നാണ്
    0.50
    桝
    0.49
    urkan
    0.47
    alakip
    0.46
    century
    0.46
    Products
    0.45
    oyin
    0.45
     သိ
    0.45
     `:`,
    0.45
    Activations Density 0.001%

    No Known Activations