© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9935
    Prev
    Next
    INDEX
    Explanations

    investment and economic opportunities

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

    politics and Saudi Vision 2030

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

    Middle Eastern political discourse

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
     فور
    0.60
     ج
    0.55
     قسمت
    0.55
     جهت
    0.54
     ف
    0.53
     چند
    0.51
    ف
    0.50
     ا
    0.50
     و
    0.49
     كلم
    0.49
    POSITIVE LOGITS
     constants
    0.54
     impulso
    0.51
     syst
    0.50
     energije
    0.50
     społecz
    0.49
     humaines
    0.49
     coexist
    0.48
     čovjek
    0.48
     humana
    0.48
     myster
    0.48
    Activations Density 0.047%

    No Known Activations