© 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. 91311
    Prev
    Next
    INDEX
    Explanations

    non followed by a word

    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
     great
    -0.78
    Sel
    -0.67
     Sel
    -0.66
     SEL
    -0.66
     truly
    -0.65
     養
    -0.65
    Ft
    -0.65
    low
    -0.63
    SEL
    -0.63
     querían
    -0.62
    POSITIVE LOGITS
    ByUserId
    0.88
     vegetarian
    0.84
    𝖼
    0.84
    ίζει
    0.82
    vegetarian
    0.82
     veg
    0.81
     Vegetarian
    0.81
    Banking
    0.81
     Đình
    0.79
     Horowitz
    0.79
    Activations Density 0.026%

    No Known Activations