© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 590
    Prev
    Next
    INDEX
    Explanations

    Quantitative blood

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

    code-related elements like function names, methods, and programming syntax.

    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
     Suggestions
    -0.72
     fis
    -0.71
     कु
    -0.69
    如下图
    -0.68
     помню
    -0.67
     fig
    -0.66
     exo
    -0.66
    评测
    -0.66
    olyb
    -0.66
    );"
    -0.65
    POSITIVE LOGITS
    ЧЕСКИ
    0.91
     patches
    0.90
    Patch
    0.89
     Patch
    0.85
    DEG
    0.81
     txt
    0.80
    patches
    0.80
    DBNull
    0.80
    quiv
    0.79
     lines
    0.78
    Activations Density 0.008%

    No Known Activations