© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 47918
    Prev
    Next
    INDEX
    Explanations

    political and legal contexts

    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_16_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
    ០
    0.86
     wasn
    0.78
     bütün
    0.75
     conhe
    0.75
    gli
    0.72
    '
    0.72
     ৬
    0.72
    f
    0.71
     يَ
    0.71
     weer
    0.70
    POSITIVE LOGITS
    ۔
    1.02
    ر
    0.96
    ن
    0.95
    ار
    0.92
    وم
    0.90
    ما
    0.86
    িতে
    0.84
    لات
    0.82
     centroids
    0.79
    리
    0.79
    Activations Density 0.000%

    No Known Activations