© 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. 90616
    Prev
    Next
    INDEX
    Explanations

    of + title or domain

    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
     post
    -0.84
     Badezimmer
    -0.80
     speculations
    -0.74
    上品
    -0.72
    induced
    -0.71
     описы
    -0.70
    好吃的
    -0.70
    が残
    -0.69
    AccountNumber
    -0.69
    Save
    -0.68
    POSITIVE LOGITS
     the
    1.09
    endpoint
    0.93
    gegen
    0.88
    ügel
    0.88
     Vainqueur
    0.88
    farande
    0.88
    𝘒
    0.86
     conquest
    0.85
     Soyez
    0.84
     <>",
    0.84
    Activations Density 0.017%

    No Known Activations