© 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. 73530
    Prev
    Next
    INDEX
    Explanations

    place names and rivers

    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
    Zdrav
    -0.91
     роботи
    -0.83
     понрави
    -0.83
    これまで
    -0.80
    知識
    -0.79
     sparked
    -0.79
     великолеп
    -0.79
    現代
    -0.79
     strangely
    -0.78
     increases
    -0.78
    POSITIVE LOGITS
    romeda
    1.17
    clerosis
    1.08
    pread
    1.08
    也只是
    1.06
    reté
    1.04
    iamo
    1.03
    artment
    1.03
    Vorlage
    1.02
    тором
    1.00
    dub
    0.99
    Activations Density 0.048%

    No Known Activations