© 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. 226879
    Prev
    Next
    INDEX
    Explanations

    international development aid

    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
     Cantonese
    0.44
     जाहीर
    0.43
     মহানগর
    0.42
     Seafood
    0.42
     redeem
    0.41
    formats
    0.41
     उपभोक्ताओं
    0.41
     CRUIS
    0.41
    諗
    0.40
     formats
    0.40
    POSITIVE LOGITS
    Peru
    0.54
    학교
    0.52
    作业
    0.52
     Malawi
    0.51
     Ethiopia
    0.51
     Guatemala
    0.50
    Ethiop
    0.50
    School
    0.50
    小学校
    0.49
     Nicaragua
    0.47
    Activations Density 0.118%

    No Known Activations