© 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. 38003
    Prev
    Next
    INDEX
    Explanations

    news headlines

    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
     її
    -1.02
     condominio
    -0.94
    水彩
    -0.92
     bağlantılar
    -0.88
    Então
    -0.86
     adverten
    -0.86
    こんに
    -0.84
    antaranya
    -0.83
     perfetto
    -0.83
    ísimas
    -0.82
    POSITIVE LOGITS
     police
    1.37
     President
    1.20
     Foreign
    1.13
     Minister
    1.12
     Vice
    1.10
     Police
    1.10
     Speaker
    1.10
    loroethene
    1.09
     implementation
    1.09
     Covid
    1.08
    Activations Density 0.042%

    No Known Activations