© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10618
    Prev
    Next
    INDEX
    Explanations

    refusing sexually explicit content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     மதிப்பு
    0.95
     Paston
    0.90
    ܢ
    0.90
     Major
    0.87
     Winston
    0.85
     Clarkson
    0.84
     Kitts
    0.84
    __/
    0.84
    ዘ
    0.80
     Cavaliers
    0.80
    POSITIVE LOGITS
    ற்ச
    1.09
    лась
    0.97
    лось
    0.91
    aucet
    0.87
     Kail
    0.87
     쉽
    0.86
     निधि
    0.83
     normalize
    0.82
    лся
    0.82
    tool
    0.82
    Activations Density 0.134%

    No Known Activations