© 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. 60689
    Prev
    Next
    INDEX
    Explanations

    http URLs

    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
     mutiara
    -1.98
    
    -1.78
     chargement
    -1.70
     libur
    -1.69
     their
    -1.67
     sayfası
    -1.65
     anadolu
    -1.59
     kalem
    -1.58
     oxu
    -1.56
     kado
    -1.55
    POSITIVE LOGITS
     that
    2.30
    但是在
    1.92
    但在
    1.79
    on
    1.71
    or
    1.70
     reinen
    1.69
     klassischen
    1.60
     talvez
    1.59
     özellikle
    1.59
     ainda
    1.59
    Activations Density 0.002%

    No Known Activations