© 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. 22-GEMMASCOPE-RES-131K
    7. 38903
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

    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_22/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
    ksan
    -0.90
    theon
    -0.83
    MapView
    -0.80
     dalamnya
    -0.80
     sekitarnya
    -0.79
     même
    -0.79
    onema
    -0.78
    hower
    -0.77
     є
    -0.76
     grasas
    -0.76
    POSITIVE LOGITS
    ｀)
    0.85
    Upp
    0.85
    lentes
    0.85
     distributes
    0.84
     cropping
    0.84
     Skywalker
    0.81
    fails
    0.80
    橡胶
    0.80
    ']='
    0.79
    Parc
    0.79
    Activations Density 0.014%

    No Known Activations