© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10805
    Prev
    Next
    INDEX
    Explanations

    companies and job roles

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

    online data entry and tagging

    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
    emek
    0.46
    ylist
    0.44
    antian
    0.44
    area
    0.43
    nurse
    0.43
    istiwa
    0.42
    areas
    0.41
    姑
    0.41
    char
    0.41
    stru
    0.41
    POSITIVE LOGITS
     KPI
    0.54
     Tencent
    0.54
     ITV
    0.48
     KPIs
    0.46
     USDT
    0.46
     QE
    0.46
     ITC
    0.46
     Flipkart
    0.44
     CME
    0.44
     IPF
    0.44
    Activations Density 0.001%

    No Known Activations