© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84170
    Prev
    Next
    INDEX
    Explanations

    course numbers and prerequisites

    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
     estudia
    -0.78
    bbies
    -0.78
     Saltar
    -0.77
    rajz
    -0.76
    Takk
    -0.75
    wob
    -0.75
    ceas
    -0.75
     办
    -0.75
     damaligen
    -0.74
    yakit
    -0.73
    POSITIVE LOGITS
     Lab
    0.89
     lab
    0.85
    lab
    0.84
     septembre
    0.83
     these
    0.83
     labs
    0.82
     zich
    0.81
    astră
    0.81
     vodou
    0.80
    Lab
    0.79
    Activations Density 0.006%

    No Known Activations