© 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. 16-GEMMASCOPE-2-RES-16K
    7. 642
    Prev
    Next
    INDEX
    Explanations

    activists progressive inclusion health waste principle

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

    sexualization of people

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

    controversial topics

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    antique
    0.40
    シンプル
    0.39
    ilor
    0.38
    線の
    0.38
     belast
    0.37
    魯
    0.37
    Z
    0.37
    S
    0.36
    ﺒ
    0.36
    ير
    0.36
    POSITIVE LOGITS
     Công
    0.52
     Kavanaugh
    0.47
     exámenes
    0.46
     McKe
    0.46
    消毒
    0.45
     SIINFEKL
    0.45
     Parenthood
    0.45
     Botox
    0.45
     Maher
    0.44
     petición
    0.44
    Activations Density 1.675%

    No Known Activations