© 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. 33006
    Prev
    Next
    INDEX
    Explanations

    ABA and legal citations

    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
    angerie
    -0.80
     congru
    -0.79
     entrée
    -0.78
    Griff
    -0.77
     literals
    -0.77
    参数
    -0.75
    邮件
    -0.74
    өздер
    -0.72
     alleg
    -0.71
     egal
    -0.71
    POSITIVE LOGITS
     Rest
    1.26
    Rest
    1.18
     REST
    0.97
     black
    0.81
     actor
    0.77
     rest
    0.75
    Meine
    0.75
    Lä
    0.74
    throp
    0.73
    晟
    0.73
    Activations Density 0.025%

    No Known Activations