© 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. 22-GEMMASCOPE-RES-131K
    7. 36250
    Prev
    Next
    INDEX
    Explanations

    code symbols and variable names

    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_22/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
    unno
    -1.16
     những
    -1.09
     Había
    -1.06
     wählen
    -1.04
     verursacht
    -1.03
    
    -1.00
     Lleva
    -0.95
    dert
    -0.95
     Estaba
    -0.94
    --){
    -0.93
    POSITIVE LOGITS
     it
    1.13
    viewWillAppear
    1.06
    zji
    1.06
    話が
    1.00
    uyor
    0.98
     plafon
    0.98
    viewDid
    0.97
     altid
    0.95
    をしていた
    0.94
     zodia
    0.94
    Activations Density 0.003%

    No Known Activations