© 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. 129585
    Prev
    Next
    INDEX
    Explanations

    bans abortion

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

    Rick Astley, urethra, stimulation, histamine, satellite

    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
     Strukt
    0.50
     компью
    0.49
     вигля
    0.49
    รือ
    0.48
    蚪
    0.48
     مشینوں
    0.47
    骖
    0.47
     файлов
    0.46
     স্ক্র
    0.46
     অনুরোধ
    0.46
    POSITIVE LOGITS
     undeniable
    0.52
     geopolitical
    0.52
     morality
    0.50
    judice
    0.49
    specifically
    0.47
    膳
    0.47
    ovým
    0.47
    conduct
    0.46
     unforgettable
    0.46
     crime
    0.46
    Activations Density 0.000%

    No Known Activations