© 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-262K
    7. 10728
    Prev
    Next
    INDEX
    Explanations

    political discourse and arguments

    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_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
    Check
    0.67
     মজার
    0.66
     bạn
    0.65
    Type
    0.64
    Battery
    0.63
     फक्त
    0.62
    Drop
    0.62
     +
    0.60
    బ్యా
    0.60
     you
    0.60
    POSITIVE LOGITS
    political
    1.13
     political
    1.10
     राजनीतिक
    1.01
    政治
    1.00
     politische
    0.95
     полити
    0.92
    politik
    0.91
     politič
    0.91
     solidar
    0.90
     রাজনৈতিক
    0.89
    Activations Density 0.034%

    No Known Activations