© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10608
    Prev
    Next
    INDEX
    Explanations

    video game consoles

    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_10/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
    There
    -1.87
    there
    -1.70
    Even
    -1.66
     Ottobre
    -1.60
    after
    -1.60
     newly
    -1.59
     навіть
    -1.58
    褔
    -1.58
    when
    -1.57
    although
    -1.57
    POSITIVE LOGITS
    螄
    1.59
      
    1.59
    ícias
    1.58
     
    1.53
     ſen
    1.50
     แต่
    1.48
     marqués
    1.46
     doit
    1.45
     distância
    1.44
    拶
    1.44
    Activations Density 0.012%

    No Known Activations