© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2110
    Prev
    Next
    INDEX
    Explanations

    authors' surnames in citations

    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
     diketahui
    -0.92
     Gen
    -0.88
     before
    -0.87
     prey
    -0.86
     dikenal
    -0.84
    明日
    -0.82
    九州
    -0.81
     With
    -0.80
    ものです
    -0.79
     menunjukkan
    -0.79
    POSITIVE LOGITS
    ಠ
    0.96
     œ
    0.88
    ACY
    0.87
    奭
    0.86
     vd
    0.86
     woh
    0.84
    めで
    0.83
    LÄ
    0.82
     牛奶
    0.82
    managed
    0.80
    Activations Density 0.025%

    No Known Activations