© 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. 22-GEMMASCOPE-RES-131K
    7. 38537
    Prev
    Next
    INDEX
    Explanations

    previous other earlier

    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_22/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
     nejen
    -1.07
    venido
    -0.95
    Precalculus
    -0.93
    هذه
    -0.91
    هذا
    -0.88
    不同的
    -0.87
    Виды
    -0.87
    语言
    -0.87
    この
    -0.85
     validés
    -0.85
    POSITIVE LOGITS
     other
    2.83
     previous
    2.33
     earlier
    1.93
    อื่น
    1.86
     previously
    1.81
    的其他
    1.76
    其他
    1.68
     других
    1.63
     diğer
    1.61
     سایر
    1.61
    Activations Density 0.058%

    No Known Activations