© 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. 75589
    Prev
    Next
    INDEX
    Explanations

    one of them, included

    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
     seperti
    -1.93
    such
    -1.70
     such
    -1.63
     như
    -1.38
    塒
    -1.34
    纐
    -1.30
     включая
    -1.29
    RESS
    -1.29
     queste
    -1.26
     такого
    -1.25
    POSITIVE LOGITS
     sabia
    1.48
     []:
    1.43
     TWO
    1.37
     enamorado
    1.36
    及其
    1.34
     hermosa
    1.34
     emphasizes
    1.31
     thinks
    1.31
     begins
    1.30
    对其
    1.28
    Activations Density 0.010%

    No Known Activations