© 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. 10-GEMMASCOPE-RES-131K
    7. 70552
    Prev
    Next
    INDEX
    Explanations

    oval, oblong, elliptical, rectangular shapes

    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
    titial
    -1.65
    {
    -1.57
     Tenemos
    -1.52
     Asegúrese
    -1.51
     Añade
    -1.51
    cisive
    -1.49
    
    -1.48
    tifiable
    -1.48
     is
    -1.48
     trecho
    -1.47
    POSITIVE LOGITS
     other
    1.96
     shaping
    1.53
     clever
    1.52
     cleverly
    1.46
     olarak
    1.41
     oval
    1.41
     relentlessly
    1.41
    ệc
    1.38
     seeking
    1.34
     込
    1.34
    Activations Density 0.064%

    No Known Activations