© 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. 111140
    Prev
    Next
    INDEX
    Explanations

    out of memory or leaks

    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
     menetapkan
    -0.74
    RouterModule
    -0.74
     melindungi
    -0.73
     memperbaiki
    -0.73
     beru
    -0.71
     memutus
    -0.70
     konstant
    -0.70
     Schultz
    -0.68
    сня
    -0.66
     Thompson
    -0.66
    POSITIVE LOGITS
     memory
    6.13
    memory
    4.94
     Memory
    4.53
    Memory
    4.50
    内存
    3.92
    MEMORY
    3.78
     MEMORY
    3.72
     памяти
    3.47
     memoria
    3.38
     mémoire
    3.22
    Activations Density 0.134%

    No Known Activations