© 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. 189976
    Prev
    Next
    INDEX
    Explanations

    application, reporting, security, children, books

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

    negative stereotypes and medical hotel

    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
     வெளி
    0.47
    ですが
    0.45
     ihren
    0.45
    ᱼ
    0.45
     должен
    0.43
     હશે
    0.41
    겠지만
    0.41
    ͇
    0.41
     gerne
    0.41
    э
    0.41
    POSITIVE LOGITS
    ف
    0.52
    Spiral
    0.49
    Pittsburgh
    0.48
    Among
    0.48
     avantages
    0.47
    Connecticut
    0.47
     vacations
    0.47
    Penn
    0.46
    Cincinnati
    0.46
     dzięki
    0.45
    Activations Density 0.001%

    No Known Activations