© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9646
    Prev
    Next
    INDEX
    Explanations

    space launches from Sichuan province

    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
     pacar
    -1.58
    bigcap
    -1.47
    baño
    -1.40
     церков
    -1.33
     тук
    -1.28
    dalam
    -1.27
     oreja
    -1.22
    :
    
    -1.22
     Préférences
    -1.21
     all
    -1.20
    POSITIVE LOGITS
     caráter
    1.67
     isolamento
    1.63
     another
    1.58
     fufficient
    1.45
     sebelum
    1.42
    醅
    1.41
    Probl
    1.40
    ଶ
    1.40
    ଵ
    1.38
    Quelles
    1.37
    Activations Density 0.117%

    No Known Activations