© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92180
    Prev
    Next
    INDEX
    Explanations

    Vladimir Putin Russia

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

    The neuron strongly activates on mentions of Russia’s president—especially “Vladimir Putin” and related titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CCS
    -0.74
    뭘
    -0.74
    MLA
    -0.71
    ACT
    -0.70
    专业的
    -0.69
    culously
    -0.69
    óta
    -0.69
    Api
    -0.69
     Examine
    -0.68
    hæ
    -0.68
    POSITIVE LOGITS
     Putin
    1.59
    Putin
    1.21
     Kremlin
    1.15
     presidential
    0.96
     judo
    0.95
     putin
    0.86
     Medvedev
    0.84
     Russia
    0.83
     gradova
    0.82
     Duma
    0.82
    Activations Density 0.018%

    No Known Activations