© 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. 60757
    Prev
    Next
    INDEX
    Explanations

    scientific literacy and molecular targeted

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

    educational content, particularly related to science, academic studies, and learning materials.

    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
    plugs
    -0.79
     ль
    -0.78
     SMC
    -0.76
    лежа
    -0.73
    ラダ
    -0.73
     Compli
    -0.71
    miers
    -0.69
    标
    -0.68
    ziplin
    -0.68
     objectively
    -0.68
    POSITIVE LOGITS
     science
    1.52
    science
    1.36
    Science
    1.36
     Science
    1.23
     scientific
    1.20
    SCIENCE
    1.13
    科学
    1.07
     SCIENCE
    1.05
     scientists
    1.01
    scientific
    0.97
    Activations Density 0.016%

    No Known Activations