© 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. 115511
    Prev
    Next
    INDEX
    Explanations

    closing or ceasing operations

    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
     khoan
    -0.84
    ёт
    -0.81
    ++);
    -0.79
    INC
    -0.79
     chưa
    -0.78
    tuj
    -0.77
    oglobulin
    -0.77
    erase
    -0.76
    開封
    -0.75
     unrestricted
    -0.75
    POSITIVE LOGITS
     closure
    4.19
     closing
    4.00
     closed
    3.53
     closures
    3.52
     Closure
    3.28
    closure
    3.19
    Closure
    3.19
    closing
    3.14
     closes
    3.11
    Closing
    3.11
    Activations Density 0.088%

    No Known Activations