© 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. 23662
    Prev
    Next
    INDEX
    Explanations

    code conjunctions

    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
    ";}
    -0.98
    してお
    -0.98
     paie
    -0.96
    pania
    -0.93
     izquier
    -0.92
    ==""){
    -0.91
    (){
    -0.91
    »։
    -0.88
     "";
    -0.88
     natale
    -0.88
    POSITIVE LOGITS
     also
    1.58
    ),
    1.41
     також
    1.36
     также
    1.25
    also
    1.18
     también
    1.15
    )
    1.13
     myös
    1.12
     zarówno
    1.09
     również
    1.09
    Activations Density 0.009%

    No Known Activations