© 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. 67705
    Prev
    Next
    INDEX
    Explanations

    political or past contexts

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

    political and foreign language concepts

    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
    冷静
    0.42
    平静
    0.41
    Perman
    0.40
    個人
    0.39
    Deaths
    0.38
    失望
    0.38
    ሥ
    0.37
    个人
    0.37
    常に
    0.37
    व्यक्ति
    0.36
    POSITIVE LOGITS
     được
    0.52
     werd
    0.47
     सियासी
    0.46
     Được
    0.41
     Orioles
    0.41
     wurde
    0.41
     Cajun
    0.41
     blev
    0.40
     politically
    0.40
     Puedes
    0.40
    Activations Density 0.059%

    No Known Activations