© 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. 77774
    Prev
    Next
    INDEX
    Explanations

    gene names and programming modules

    np_acts-logits-general · gemini-2.5-flash-lite

    code blocks or programming-related content in technical questions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ubs
    -0.91
    tiglie
    -0.83
    嵋
    -0.81
     حمل
    -0.80
    mainWindow
    -0.77
     AFFAIRS
    -0.74
    asinya
    -0.73
    Œ
    -0.72
    IService
    -0.72
     Nedir
    -0.71
    POSITIVE LOGITS
    ostí
    0.77
     لص
    0.75
     unchecked
    0.75
    问题的
    0.75
    ложи
    0.73
    ⽤
    0.73
     Hoang
    0.73
     لاع
    0.71
    チア
    0.71
    osof
    0.69
    Activations Density 0.039%

    No Known Activations