© 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. 41688
    Prev
    Next
    INDEX
    Explanations

    LEGO, Oreo, WiFi, Le, code comments

    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
    7
    -2.94
    la
    -2.52
    at
    -2.45
    4
    -2.45
    5
    -2.41
    m
    -2.41
    3
    -2.38
    潆
    -2.34
    ri
    -2.34
    i
    -2.33
    POSITIVE LOGITS
     pembentukan
    2.81
     numerosos
    2.33
    幸運
    2.19
     Есть
    2.16
     their
    2.16
     There
    2.13
     explicado
    2.09
    法规
    2.09
     numerosas
    2.08
     peristiwa
    2.08
    Activations Density 0.001%

    No Known Activations