© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7064
    Prev
    Next
    INDEX
    Explanations

    criminal justice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bilayer
    1.76
    投注
    1.67
    LIED
    1.67
    ocalyptic
    1.65
    ospitals
    1.62
    ieken
    1.62
    ancake
    1.61
    wamy
    1.61
     publie
    1.60
    닫
    1.58
    POSITIVE LOGITS
    骜
    1.76
    ea
    1.54
    background
    1.52
    test
    1.47
    sons
    1.45
     background
    1.43
    ech
    1.43
    otov
    1.41
    代码
    1.40
    ei
    1.38
    Activations Density 0.008%

    No Known Activations