© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43364
    Prev
    Next
    INDEX
    Explanations

    look at this

    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
    ’
    -1.65
     will
    -1.48
    好在
    -1.47
     veľmi
    -1.30
     Rezepte
    -1.29
     veľa
    -1.27
     každý
    -1.24
     setiap
    -1.23
    více
    -1.22
     “
    -1.21
    POSITIVE LOGITS
     (...)
    1.45
    nachron
    1.44
     LUMI
    1.43
     tarifs
    1.39
     Wanita
    1.34
    hauled
    1.34
    
    1.34
     collaborateurs
    1.34
     Giochi
    1.29
    oretical
    1.27
    Activations Density 0.013%

    No Known Activations