© 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. 205964
    Prev
    Next
    INDEX
    Explanations

    right or ability to

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

    non-English financial 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
    created
    0.51
    leaving
    0.50
    relative
    0.49
     কার্যত
    0.48
    心情
    0.48
    。）
    0.47
    不怕
    0.47
    。
    0.46
    保留
    0.46
     ∀
    0.46
    POSITIVE LOGITS
     काली
    0.52
     ર
    0.48
     compañías
    0.46
     mío
    0.46
     convertir
    0.45
     naciones
    0.45
     ellos
    0.44
     tomorrow
    0.44
     financiero
    0.44
     Buckeye
    0.44
    Activations Density 0.000%

    No Known Activations