© 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. 324
    Prev
    Next
    INDEX
    Explanations

    Instead, Rather

    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
     not
    -2.94
     không
    -2.56
     δεν
    -2.39
     не
    -2.30
     tidak
    -2.22
     ikke
    -2.22
    ไม่ได้
    -2.20
     also
    -2.19
     no
    -2.19
     nicht
    -2.05
    POSITIVE LOGITS
     vielmehr
    1.85
    而是
    1.59
     наоборот
    1.38
     opting
    1.30
     lieber
    1.30
     inkább
    1.27
    :{
    1.20
     opted
    1.20
     فقط
    1.19
     like
    1.18
    Activations Density 0.031%

    No Known Activations