© 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. 10612
    Prev
    Next
    INDEX
    Explanations

    sexually suggestive 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
     regarding
    1.03
     additionally
    1.00
     likewise
    0.98
    ;.
    0.91
    に追加
    0.90
     ;;
    0.89
    regarding
    0.88
     時間
    0.87
     admittance
    0.85
     때문에
    0.85
    POSITIVE LOGITS
    )】
    0.94
    ))}
    0.90
     žen
    0.89
     Appear
    0.88
     एवरी
    0.87
     Immediately
    0.86
    ̌
    0.86
    om
    0.85
     Iterate
    0.85
    皘
    0.85
    Activations Density 0.138%

    No Known Activations