© 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. 66080
    Prev
    Next
    INDEX
    Explanations

    Primrose Located published

    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
     what
    -1.16
    PLATFORM
    -0.95
    mancy
    -0.86
    IonicModule
    -0.85
    тельность
    -0.83
     пальто
    -0.83
    "../
    -0.82
     একটি
    -0.80
    ctus
    -0.80
     Platform
    -0.80
    POSITIVE LOGITS
     配件
    1.08
    骉
    0.96
    Discounts
    0.88
     Spraw
    0.88
    Lugares
    0.86
    Mange
    0.85
    έρ
    0.85
    Presenta
    0.84
    Buen
    0.84
    Attacks
    0.84
    Activations Density 0.001%

    No Known Activations