© 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. 10-GEMMASCOPE-RES-131K
    7. 105231
    Prev
    Next
    INDEX
    Explanations

    mining and technology

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

    text related to mining, petroleum extraction, and industrial operations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     druhé
    -1.61
     religieuses
    -1.57
     Glaubens
    -1.55
     Unterrichts
    -1.55
     дѣ
    -1.52
     Theologie
    -1.50
     kuhusu
    -1.50
     учащихся
    -1.49
    Özel
    -1.48
    Açık
    -1.47
    POSITIVE LOGITS
     informó
    1.57
    ῆ
    1.47
    נְ
    1.45
     препара
    1.43
    אַ
    1.41
     الصيف
    1.38
     detalló
    1.38
     dégustation
    1.30
     detailed
    1.30
     optimieren
    1.30
    Activations Density 0.118%

    No Known Activations