© 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. 31-GEMMASCOPE-2-RES-262K
    7. 6103
    Prev
    Next
    INDEX
    Explanations

    sexual objectification and exploitation

    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_31_width_262k_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
    <b>
    0.40
    key
    0.38
    S
    0.38
     key
    0.37
    ometimes
    0.37
                 
    0.37
     odpowied
    0.37
     சில
    0.36
               
    0.36
    ṣ
    0.36
    POSITIVE LOGITS
     এতটা
    0.85
    这么
    0.84
     столь
    0.83
     такого
    0.83
    如此
    0.82
     ilyen
    0.80
     such
    0.79
    這麼
    0.78
     इतनी
    0.77
    这么多
    0.74
    Activations Density 0.532%

    No Known Activations