© 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. 103373
    Prev
    Next
    INDEX
    Explanations

    Internet Corporation, Archive, Explorer, Protocol

    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
     immaculate
    -0.95
     웹툰
    -0.94
     monotonous
    -0.91
    "])){
    -0.91
    ां
    -0.90
    kegaard
    -0.90
     ornate
    -0.89
     wissenschaft
    -0.88
     πρώ
    -0.88
    ご了承ください
    -0.87
    POSITIVE LOGITS
     Explorer
    1.27
     explorer
    1.16
     café
    1.02
     Relay
    0.98
     Internet
    0.94
     Protocol
    0.93
     cafe
    0.90
     cafes
    0.90
    ższe
    0.89
    connected
    0.88
    Activations Density 0.020%

    No Known Activations