© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56470
    Prev
    Next
    INDEX
    Explanations

    languages and scripts

    np_acts-logits-general · gemini-2.5-flash-lite

    two spies or travelers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     صہیونیوں
    0.47
     proactively
    0.46
     circunfer
    0.45
    गोलिक
    0.44
    Verizon
    0.43
    மாகவும்
    0.43
    getActive
    0.43
    转
    0.43
    Shark
    0.42
    ‌ترین
    0.42
    POSITIVE LOGITS
     など
    0.47
     म
    0.47
     ವಿದ್ಯ
    0.46
     א
    0.43
     ய
    0.43
     నాయ
    0.43
     아주
    0.43
     ന
    0.42
     знает
    0.42
     ਨ
    0.42
    Activations Density 0.000%

    No Known Activations