© 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. 87038
    Prev
    Next
    INDEX
    Explanations

    scientific/medical journals

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

    academic paper citation identifiers and reference keys in scholarly articles.

    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
     producto
    -0.74
     kesim
    -0.74
     سرا
    -0.72
    смот
    -0.71
    ี้ย
    -0.70
     Two
    -0.68
    (*(
    -0.68
     product
    -0.68
     وزیر
    -0.67
    stddef
    -0.66
    POSITIVE LOGITS
     MD
    1.45
    MD
    1.25
     md
    1.08
     Energies
    1.05
    Md
    1.01
     MDM
    0.98
     Sustainability
    0.98
    md
    0.96
    Sustainability
    0.94
     tranches
    0.92
    Activations Density 0.091%

    No Known Activations