© 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. 90820
    Prev
    Next
    INDEX
    Explanations

    circuit court divisions

    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
     to
    -0.81
     तक
    -0.75
     результа
    -0.72
     tarta
    -0.71
    %{
    -0.69
     based
    -0.69
    colato
    -0.66
    ervis
    -0.65
    Calcul
    -0.64
     passport
    -0.64
    POSITIVE LOGITS
    办
    0.85
     Gypsum
    0.76
    exists
    0.75
    のかもしれません
    0.75
    collision
    0.75
     pomocą
    0.75
     operas
    0.74
    になりました
    0.74
    置く
    0.73
     empezaron
    0.72
    Activations Density 0.033%

    No Known Activations