© 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. 34-GEMMASCOPE-RES-131K
    7. 30833
    Prev
    Next
    INDEX
    Explanations

    project concept

    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
    回答
    -0.77
    quran
    -0.72
    atguigu
    -0.71
    cursos
    -0.70
    milan
    -0.69
     kalimat
    -0.67
     kemenangan
    -0.66
    catalogue
    -0.66
    spanish
    -0.65
    GEBURTS
    -0.65
    POSITIVE LOGITS
     project
    2.53
    project
    2.11
    Project
    1.73
     Project
    1.72
     projeto
    1.70
     proyecto
    1.68
     proiect
    1.59
     PROJECT
    1.59
     پروژه
    1.58
     projet
    1.56
    Activations Density 0.079%

    No Known Activations