© 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. 10067
    Prev
    Next
    INDEX
    Explanations

    political party roles

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

    political parties and power

    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_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
     WaitFor
    0.50
    蔬
    0.47
     साझेदारी
    0.46
     साझे
    0.44
     업체
    0.44
     ಸರ್ಕಾರ
    0.44
     सरकार
    0.43
     pemerintah
    0.43
     സര്‍ക്കാര്‍
    0.43
    弧
    0.42
    POSITIVE LOGITS
    Party
    1.34
     party
    1.31
     Party
    1.31
    黨
    1.31
    党
    1.27
    党员
    1.26
    party
    1.24
     पार्टी
    1.20
     PARTY
    1.20
     پارٹی
    1.16
    Activations Density 0.146%

    No Known Activations