© 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. 118161
    Prev
    Next
    INDEX
    Explanations

    Generated by Django

    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
    ར
    -0.69
    HCO
    -0.69
     Parlament
    -0.68
    唢
    -0.68
    PSC
    -0.66
     còn
    -0.66
    トッピング
    -0.65
    XIM
    -0.64
     parlament
    -0.64
     Signs
    -0.64
    POSITIVE LOGITS
     sooth
    0.73
    Ǹ
    0.72
    𝘃
    0.71
    forsch
    0.71
     Searle
    0.71
    addAttribute
    0.70
     mukaan
    0.69
     Higgs
    0.69
     الأس
    0.67
    tidal
    0.66
    Activations Density 0.058%

    No Known Activations