© 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. 82996
    Prev
    Next
    INDEX
    Explanations

    safely with shield

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

    malware and system faults

    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
    Not in Any Lists

    No Comments

    Negative Logits
    quando
    0.59
    ções
    0.51
    ністю
    0.50
     झाल्यानंतर
    0.50
    adrat
    0.49
    ца
    0.48
     екс
    0.48
    리
    0.48
    peanut
    0.48
    đ
    0.47
    POSITIVE LOGITS
     Humanitarian
    0.42
     রকম
    0.42
     ร้อย
    0.42
     Demographic
    0.41
     ξε
    0.40
     Communication
    0.40
     قومی
    0.40
    പ്പെടെ
    0.40
     CNN
    0.40
     수도
    0.38
    Activations Density 0.001%

    No Known Activations