© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 70976
    Prev
    Next
    INDEX
    Explanations

    killed during, sources and

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

    Black people are a monolith

    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
    Negative Logits
     Admiral
    0.44
    ನಗೆ
    0.43
     入り
    0.43
    藍
    0.43
     Shyam
    0.43
    ДУ
    0.43
     Пів
    0.42
    ebilir
    0.42
     पॉपुलर
    0.41
     קר
    0.41
    POSITIVE LOGITS
    ޒ
    0.44
    ുവ
    0.44
     metabolismo
    0.42
     حفاظت
    0.42
     hablando
    0.41
    una
    0.41
    灶
    0.40
     giro
    0.40
     vantaggio
    0.40
     manejo
    0.40
    Activations Density 0.000%

    No Known Activations