© 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. 10-GEMMASCOPE-RES-131K
    7. 12208
    Prev
    Next
    INDEX
    Explanations

    bringing with them

    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_10/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
            
    -1.70
    {
    -1.55
     wykonane
    -1.52
    櫪
    -1.50
     feiner
    -1.48
     לכם
    -1.47
     cansado
    -1.45
     gefallen
    -1.45
    -1.43
    ↵
    -1.40
    POSITIVE LOGITS
     to
    2.33
     Notably
    1.76
    sembles
    1.72
     Such
    1.71
     in
    1.61
     Moreover
    1.59
    فعل
    1.58
     To
    1.58
     Of
    1.54
     Especially
    1.53
    Activations Density 0.005%

    No Known Activations