© 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. 7261
    Prev
    Next
    INDEX
    Explanations

    frameworks and contexts

    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
    ENR
    -0.74
    Причины
    -0.70
    Citations
    -0.69
    Techniques
    -0.67
    気軽に
    -0.67
    Grp
    -0.65
    關鍵
    -0.64
    理由は
    -0.63
    мыми
    -0.63
    épar
    -0.63
    POSITIVE LOGITS
     framework
    5.03
    framework
    3.86
     рамках
    3.78
     frame
    3.78
     frameworks
    3.66
    框架
    3.52
     frames
    3.41
     Rahmen
    3.34
     Framework
    3.03
     FRAMEWORK
    3.03
    Activations Density 0.072%

    No Known Activations