© 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. 38275
    Prev
    Next
    INDEX
    Explanations

    special characters and technical terms

    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
    ondern
    -0.85
    心脏
    -0.79
     Viitattu
    -0.78
    anganese
    -0.74
     sposób
    -0.71
    скар
    -0.71
    運営
    -0.71
     ]);
    -0.70
    wanzig
    -0.70
    んです
    -0.69
    POSITIVE LOGITS
     donations
    1.38
     donation
    1.04
    Donations
    0.94
     enquiries
    0.94
     family
    0.94
     flowers
    0.92
     any
    0.92
     Family
    0.91
    Would
    0.91
     messages
    0.87
    Activations Density 0.007%

    No Known Activations