© 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. 22-GEMMASCOPE-RES-131K
    7. 71649
    Prev
    Next
    INDEX
    Explanations

    sole reproducers, sole definitive hosts, sole circuit

    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_22/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
    декса
    -1.00
    contributors
    -0.81
    sommer
    -0.80
    ofing
    -0.78
     ķ
    -0.77
    muir
    -0.77
    Viitteet
    -0.77
    ческих
    -0.77
     pirm
    -0.76
    beit
    -0.76
    POSITIVE LOGITS
    BACKGROUND
    0.80
     governmental
    0.80
     infrastructure
    0.77
    Government
    0.76
    government
    0.76
     government
    0.75
     duradero
    0.75
     دیگران
    0.74
     extérieure
    0.73
     leadership
    0.73
    Activations Density 0.273%

    No Known Activations