© 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. 184104
    Prev
    Next
    INDEX
    Explanations

    political reforms and subsidies

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

    depending on variation

    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
    लोगों
    0.53
    ו
    0.52
    ザ
    0.50
    あり
    0.47
    לו
    0.47
     لوبې
    0.46
    דו
    0.46
    ﻟ
    0.46
    騒
    0.46
    мы
    0.46
    POSITIVE LOGITS
     reforms
    0.61
     اصلاح
    0.50
     changes
    0.48
     อนุ
    0.47
     inefficiencies
    0.47
     Reforms
    0.46
     anod
    0.46
     ब्ले
    0.46
     subsidies
    0.45
    ings
    0.45
    Activations Density 0.001%

    No Known Activations