© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7514
    Prev
    Next
    INDEX
    Explanations

    political/geopolitical concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    1.16
     audible
    1.07
     earrings
    1.06
     shampoo
    1.05
     conversational
    1.05
     workpiece
    1.05
     accuracy
    1.05
     lettering
    1.05
    querdo
    1.04
    ०
    1.03
    POSITIVE LOGITS
     geopol
    1.52
     gobiernos
    1.52
     রাজনৈতিক
    1.44
    政治
    1.43
    Political
    1.41
     políticos
    1.38
     राजनीतिक
    1.34
    พวกเขา
    1.34
     multinationals
    1.34
     полити
    1.30
    Activations Density 0.742%

    No Known Activations