© 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. 14434
    Prev
    Next
    INDEX
    Explanations

    ICC, Criminal, Council, court, COMMISSION

    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
    تیجه
    -2.98
    。「
    -2.98
    autogui
    -2.92
    It
    -2.86
    There
    -2.78
    扞
    -2.67
    蘩
    -2.58
    However
    -2.55
     antiquated
    -2.53
    Another
    -2.50
    POSITIVE LOGITS
    廰
    2.72
    鞴
    2.61
    鵙
    2.56
     Diſ
    2.47
    ate
    2.47
     たっぷり
    2.47
     Perſ
    2.42
    ⬮
    2.39
    鹟
    2.39
    過了
    2.34
    Activations Density 0.001%

    No Known Activations