© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 802
    Prev
    Next
    INDEX
    Explanations

    slave labor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_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
    áciu
    0.75
    ку
    0.69
    ين
    0.69
    il
    0.66
    ități
    0.63
    ام
    0.61
    지
    0.61
    カ
    0.61
    ला
    0.58
    лили
    0.58
    POSITIVE LOGITS
     slave
    0.93
     slaves
    0.93
     Slave
    0.89
    </h4>
    0.85
    </h1>
    0.84
    <0x0D>
    0.83
     Slavery
    0.83
    slave
    0.83
     slavery
    0.82
    </h2>
    0.82
    Activations Density 0.018%

    No Known Activations