© 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. 47473
    Prev
    Next
    INDEX
    Explanations

    condition configuration settings

    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
     it
    -2.02
     by
    -1.62
     was
    -1.44
     hacer
    -1.40
     had
    -1.40
     when
    -1.40
     soothing
    -1.39
     wants
    -1.34
     seeks
    -1.34
     there
    -1.31
    POSITIVE LOGITS
    potentially
    1.50
     刺繍
    1.48
    Possibly
    1.46
    Hopefully
    1.44
    Fortunately
    1.40
    seamnă
    1.40
    っているので
    1.39
     dreamstime
    1.38
    Luckily
    1.38
    Eventually
    1.36
    Activations Density 0.002%

    No Known Activations