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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7086
    Prev
    Next
    INDEX
    Explanations

    communism, socialism, and Marxism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    érieures
    0.50
    靥
    0.49
    节省
    0.48
    赌
    0.46
    蜈
    0.46
    贵
    0.46
    chende
    0.46
    缕
    0.46
    护理
    0.45
    镁
    0.45
    POSITIVE LOGITS
     socialist
    1.62
     Marxist
    1.55
     communist
    1.55
     Communist
    1.48
     socialism
    1.47
     Marxism
    1.45
     Socialist
    1.43
     Socialism
    1.41
     socialista
    1.30
     socialists
    1.30
    Activations Density 0.116%

    No Known Activations