© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1284
    Prev
    Next
    INDEX
    Explanations

    sexual connotations

    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_40_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
    <u>
    0.31
    There
    0.30
     There
    0.29
    也可以
    0.27
     phenomenon
    0.26
    lli
    0.26
     Wikipedia
    0.25
    
    0.25
    <unused2130>
    0.24
     ‌
    0.24
    POSITIVE LOGITS
     مذکور
    0.37
     بیاکتنې
    0.35
     eten
    0.33
     muziek
    0.31
    ເພດ
    0.31
     restantes
    0.31
     cadeaux
    0.31
     różnych
    0.30
     جوړونکي
    0.30
     privind
    0.30
    Activations Density 0.154%

    No Known Activations