© 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. 73383
    Prev
    Next
    INDEX
    Explanations

    ISO 9001 audit

    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
     cenu
    -0.91
     tarifleri
    -0.77
    違和
    -0.71
     картофе
    -0.71
     хозя
    -0.71
    zeß
    -0.71
     galeri
    -0.70
     investir
    -0.70
     advertisers
    -0.69
    臨時
    -0.69
    POSITIVE LOGITS
     auditors
    1.84
     auditor
    1.81
     audit
    1.66
     ISO
    1.59
     Auditor
    1.56
     auditing
    1.45
    ISO
    1.43
     Auditors
    1.39
    Auditor
    1.35
    Audit
    1.32
    Activations Density 0.013%

    No Known Activations