© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4262
    Prev
    Next
    INDEX
    Explanations

    rape prevention and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    E
    0.63
    D
    0.63
    Summer
    0.61
    窟
    0.61
    olie
    0.61
    P
    0.59
    S
    0.58
    陛
    0.55
    M
    0.55
    T
    0.55
    POSITIVE LOGITS
     paying
    1.02
     Eating
    0.97
     Paying
    0.96
     Beef
    0.93
     Pay
    0.89
     Av
    0.88
     Comm
    0.85
     Every
    0.84
     অন্য
    0.83
    బ్‌
    0.83
    Activations Density 0.009%

    No Known Activations