© 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. 36839
    Prev
    Next
    INDEX
    Explanations

    empresarial y de transporte

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

    focus on

    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
    唠
    0.49
    了出来
    0.49
    锵
    0.48
    一组
    0.47
    建议
    0.47
    回来了
    0.47
    强调
    0.46
    madı
    0.46
     Verbal
    0.46
    垪
    0.46
    POSITIVE LOGITS
     agricultura
    0.69
     and
    0.66
     agribusiness
    0.62
     industria
    0.56
     aquaculture
    0.56
    and
    0.54
     agriculture
    0.54
     pharmaceuticals
    0.53
     banking
    0.52
     transporte
    0.52
    Activations Density 0.000%

    No Known Activations