© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 20333
    Prev
    Next
    INDEX
    Explanations

    religion and protected characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     continuación
    0.92
    בע
    0.89
     zudem
    0.89
     liées
    0.87
     berikut
    0.83
    သွယ်
    0.81
    ouvrir
    0.80
    ឮ
    0.80
    éléments
    0.80
     baseado
    0.80
    POSITIVE LOGITS
     accommodations
    1.09
     selections
    0.85
     preferences
    0.81
     lovingly
    0.78
     Preferences
    0.77
     tallied
    0.75
     choice
    0.75
     expenses
    0.75
     selection
    0.75
     choices
    0.74
    Activations Density 0.008%

    No Known Activations