© 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. 110820
    Prev
    Next
    INDEX
    Explanations

    Indonesian, Malay place names

    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
     Kop
    -0.81
     obra
    -0.75
     beina
    -0.73
     بسیاری
    -0.72
     capo
    -0.72
     प्रोड
    -0.71
    zip
    -0.71
     temperatures
    -0.70
    bearer
    -0.70
    ိ
    -0.69
    POSITIVE LOGITS
     particulière
    0.86
     článku
    0.82
     vacancy
    0.80
     esquecer
    0.79
     potom
    0.79
     différente
    0.77
     recitation
    0.77
     lutar
    0.77
     stärker
    0.75
    sschutz
    0.74
    Activations Density 0.004%

    No Known Activations