© 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. 119192
    Prev
    Next
    INDEX
    Explanations

    public class declarations

    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
    print
    -0.75
     square
    -0.71
     مد
    -0.71
     squared
    -0.68
     Dwyer
    -0.67
     chips
    -0.66
    nc
    -0.65
     print
    -0.65
    ندان
    -0.65
    žia
    -0.65
    POSITIVE LOGITS
     Trimble
    0.68
    Holes
    0.66
    钠
    0.63
    eut
    0.63
    iş
    0.62
    дук
    0.62
    לב
    0.62
     Antique
    0.61
     ozna
    0.61
    declarations
    0.60
    Activations Density 0.088%

    No Known Activations