© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7278
    Prev
    Next
    INDEX
    Explanations

    .pdf or scientific papers

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

    academic citation and reference formats in scholarly documents.

    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
     or
    -1.27
     for
    -0.94
     (
    -0.91
     they
    -0.87
     of
    -0.86
     gradually
    -0.86
     especially
    -0.85
     most
    -0.85
     many
    -0.85
     really
    -0.84
    POSITIVE LOGITS
    Titel
    1.07
    pdf
    1.05
    titel
    1.05
    bluza
    1.03
    title
    1.02
    Gön
    0.98
    タイトル
    0.98
    
    0.97
    Carrière
    0.96
     trám
    0.96
    Activations Density 0.000%

    No Known Activations