© 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. 166650
    Prev
    Next
    INDEX
    Explanations

    insurance claim refund loss

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

    relation to specific items

    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
     किताबों
    0.50
    ›
    0.49
    м
    0.48
    midrule
    0.47
    ρα
    0.47
    τυ
    0.46
    ITY
    0.45
    ରା
    0.45
    𝑦
    0.45
    뿅
    0.45
    POSITIVE LOGITS
     Provost
    0.49
     Sports
    0.46
     Buyer
    0.46
     افرادی
    0.46
     Cambodian
    0.45
     Japanese
    0.44
     Doncaster
    0.44
     करण्यास
    0.44
     War
    0.43
     Hot
    0.43
    Activations Density 0.000%

    No Known Activations