© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99946
    Prev
    Next
    INDEX
    Explanations

    justice and related concepts

    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_10/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
    荜
    -2.06
    </h3>
    -2.06
     业
    -1.98
    跸
    -1.98
     большая
    -1.95
    </strong>
    -1.94
    嫗
    -1.93
    箭头
    -1.85
    ꦒ
    -1.83
    哢
    -1.82
    POSITIVE LOGITS
    ↵
    2.42
    4
    2.39
     icona
    2.11
    Also
    2.08
     aussit
    2.06
    ſu
    2.05
    少し
    1.95
    那些
    1.95
    在
    1.94
    We
    1.88
    Activations Density 0.008%

    No Known Activations