© 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. 98398
    Prev
    Next
    INDEX
    Explanations

    WikiLeaks, Wikipedia, wikiHow, Wiktionary

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     помещений
    -0.73
    不仅
    -0.73
    savefig
    -0.73
     besonderes
    -0.73
    raison
    -0.72
    1
    -0.72
     previously
    -0.72
    を考える
    -0.70
    裏面
    -0.70
    …(
    -0.69
    POSITIVE LOGITS
    Leaks
    1.11
    wijs
    1.01
    农场
    0.98
     нази
    0.96
     Markup
    0.87
    𝘱
    0.86
    дим
    0.86
    paedia
    0.85
    Calc
    0.84
     Wik
    0.84
    Activations Density 0.011%

    No Known Activations