© 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. 48168
    Prev
    Next
    INDEX
    Explanations

    specific domains and their components

    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
    точници
    -1.24
    筊
    -1.23
     amélior
    -1.06
    شكرا
    -1.03
    ございました
    -1.03
    χεία
    -1.03
    Jawab
    -1.01
     menghubungi
    -1.00
    Шаг
    -1.00
    entrums
    -0.97
    POSITIVE LOGITS
     of
    4.22
     that
    2.33
     aspect
    1.88
     you
    1.65
     process
    1.55
     we
    1.54
     they
    1.48
     component
    1.46
     situation
    1.46
     environment
    1.38
    Activations Density 0.364%

    No Known Activations