© 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. 94448
    Prev
    Next
    INDEX
    Explanations

    health and wellbeing advice

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

    obtain verification pipelines movement security therefore borrow

    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
     warning
    0.46
     complicating
    0.44
    ubj
    0.43
     insecticide
    0.43
    稞
    0.42
     Broncos
    0.41
     Inspectors
    0.41
     た
    0.41
     fanc
    0.41
     Pip
    0.40
    POSITIVE LOGITS
     зберіга
    0.48
    之後
    0.47
     دعوت
    0.46
     اولاد
    0.46
     بدن
    0.46
    身體
    0.45
    伍章
    0.45
     знаходиться
    0.44
     آزادی
    0.43
     मानवता
    0.43
    Activations Density 0.000%

    No Known Activations