© 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. 59672
    Prev
    Next
    INDEX
    Explanations

    LINQ to SQL, Entities, XML, Expressions

    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
     トップ
    -0.88
     impostor
    -0.84
    ﻱ
    -0.83
    ologi
    -0.83
     truss
    -0.79
    ⊄
    -0.79
     Regula
    -0.78
     mares
    -0.77
    抜群
    -0.75
     leek
    -0.75
    POSITIVE LOGITS
    館
    0.85
     expressions
    0.84
     Quaternion
    0.79
     vertebrate
    0.78
     molecule
    0.76
    ૌ
    0.76
     vaccination
    0.75
     кризи
    0.74
    怠
    0.73
     monitoring
    0.72
    Activations Density 0.007%

    No Known Activations