© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108243
    Prev
    Next
    INDEX
    Explanations

    righteousness and justice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Opfer
    -0.73
    hapus
    -0.70
    说话
    -0.69
    이다
    -0.68
    Gee
    -0.66
    ighters
    -0.65
     utilizzando
    -0.65
    HeaderView
    -0.65
     Success
    -0.63
    roy
    -0.63
    POSITIVE LOGITS
     righteousness
    3.38
     righteous
    2.86
     Righteous
    2.72
    righteous
    2.63
    义
    1.45
    義
    1.35
     justicia
    1.25
     upright
    1.20
    teous
    1.16
     justific
    1.13
    Activations Density 0.021%

    No Known Activations