© 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. 5415
    Prev
    Next
    INDEX
    Explanations

    political parties and ideologies

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

    political discourse and ideologies

    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
     খাবার
    0.49
     완료
    0.46
    密封
    0.45
    传输
    0.45
     scintillation
    0.45
    อุปกรณ์
    0.45
    样品
    0.45
    辂
    0.43
     plated
    0.42
    ເຄື່ອງ
    0.42
    POSITIVE LOGITS
     ideological
    0.96
     políticos
    0.96
     populist
    0.94
     politič
    0.94
     political
    0.91
     полити
    0.91
     राजनीतिक
    0.91
     conservatives
    0.89
    political
    0.89
     politischen
    0.88
    Activations Density 0.451%

    No Known Activations