© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1702
    Prev
    Next
    INDEX
    Explanations

    sexual topics and crime

    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_17_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
    ↵
    1.13
     ...
    0.92
    .....
    0.90
    ...
    0.90
    ↵↵↵
    0.89
    \
    0.87
     Итак
    0.87
    :\
    0.86
        
    0.85
     delà
    0.85
    POSITIVE LOGITS
     tattoo
    1.98
     tattoos
    1.94
     rapper
    1.92
     billionaire
    1.91
     celebrity
    1.90
     sculptures
    1.88
     satirical
    1.87
     celebrities
    1.86
     prostitution
    1.83
     pornography
    1.82
    Activations Density 0.994%

    No Known Activations