© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3635
    Prev
    Next
    INDEX
    Explanations

    credit limits and banking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    achd
    0.57
    PanelVisual
    0.57
    Acceler
    0.56
    El
    0.54
    Az
    0.54
    Analyzer
    0.54
    EventRecorder
    0.53
    Flavor
    0.53
    </h2>
    0.52
    )}$.
    0.52
    POSITIVE LOGITS
     బ్యాం
    0.63
     overdraft
    0.61
     банка
    0.59
     కాల్
    0.58
     ব্যাঙ্ক
    0.57
     банков
    0.56
    ុន
    0.55
     بینک
    0.55
     بنائیں
    0.55
    年会
    0.55
    Activations Density 0.085%

    No Known Activations