© 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. 23767
    Prev
    Next
    INDEX
    Explanations

    scientific trials and expert opinions

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

    headings, section markers, and formatting elements in academic or scientific papers.

    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
    ържа
    -0.87
     Dumb
    -0.86
     Quran
    -0.83
    Seguro
    -0.79
     METHODOLOGY
    -0.78
    燁
    -0.78
     conseguido
    -0.77
    ásticos
    -0.76
    的一个
    -0.76
    มาณ
    -0.76
    POSITIVE LOGITS
     significance
    1.16
    Trial
    1.07
    trial
    1.01
     lay
    0.99
     trial
    0.98
     SIGNIFIC
    0.91
    impact
    0.90
     Trial
    0.88
    Plain
    0.88
    video
    0.86
    Activations Density 0.321%

    No Known Activations