© 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. 159863
    Prev
    Next
    INDEX
    Explanations

    financial transactions and advice

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

    finance and business transactions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ט
    0.50
    ktron
    0.47
     qal
    0.46
    PROTON
    0.46
    ту
    0.46
    рта
    0.45
     стихо
    0.45
     wiadomo
    0.45
    AKE
    0.45
    }}$.
    0.43
    POSITIVE LOGITS
     Directly
    0.48
     borrowings
    0.48
    ,-\
    0.47
     рэгістра
    0.46
    บน
    0.43
     असतात
    0.43
     Returning
    0.43
    payments
    0.43
    returning
    0.42
     Quando
    0.42
    Activations Density 0.001%

    No Known Activations