© 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. 34955
    Prev
    Next
    INDEX
    Explanations

    language codes and geopolitical entities

    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
    uelle
    -0.87
    miesz
    -0.87
    žad
    -0.85
    Tokens
    -0.85
    ⇁
    -0.84
    menta
    -0.82
     appartenant
    -0.82
    yttää
    -0.82
    サイズ
    -0.81
    ｍ
    -0.81
    POSITIVE LOGITS
     прошла
    0.90
     抓
    0.81
     or
    0.76
     ligero
    0.75
     führten
    0.75
     such
    0.75
    座位
    0.74
    锣
    0.72
    ullan
    0.72
    歉
    0.71
    Activations Density 0.011%

    No Known Activations