© 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. 90102
    Prev
    Next
    INDEX
    Explanations

    error codes and numbers

    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
    أما
    -0.85
    頓
    -0.75
     vôtre
    -0.74
    गी
    -0.73
    鑑
    -0.70
    Day
    -0.69
    編
    -0.69
     neighbouring
    -0.69
    كما
    -0.68
    tése
    -0.68
    POSITIVE LOGITS
    وبر
    0.79
     windows
    0.77
    荨
    0.75
    Hr
    0.75
     polys
    0.74
     tenisky
    0.74
     διά
    0.73
     hr
    0.73
     специфи
    0.72
     Element
    0.71
    Activations Density 0.060%

    No Known Activations