© 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. 54058
    Prev
    Next
    INDEX
    Explanations

    WHO principles of perinatal care

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

    technical information about satellite and space technology.

    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
     minutter
    -0.82
     البلاد
    -0.80
    院校
    -0.77
     lys
    -0.77
     sehr
    -0.74
     catalysts
    -0.73
     спортс
    -0.73
     furl
    -0.73
     soils
    -0.71
    Ց
    -0.71
    POSITIVE LOGITS
     constellation
    1.08
     Loon
    0.97
     Kui
    0.96
    Coverage
    0.91
     LEO
    0.90
     Coverage
    0.88
    ohistochemistry
    0.88
    LEO
    0.83
    beto
    0.80
     coverage
    0.79
    Activations Density 0.009%

    No Known Activations