© 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. 129786
    Prev
    Next
    INDEX
    Explanations

    paintGL

    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
     blusa
    -1.08
     Staat
    -1.05
    TNode
    -1.01
    .},
    -1.00
     Noten
    -0.99
    greja
    -0.98
    atoto
    -0.98
    Historically
    -0.97
    ConfigureAwait
    -0.97
    struzioni
    -0.96
    POSITIVE LOGITS
     my
    1.04
     this
    1.04
    self
    1.03
     has
    0.99
    this
    0.96
     волшеб
    0.93
     wyłą
    0.90
     will
    0.90
     had
    0.90
     orien
    0.89
    Activations Density 0.011%

    No Known Activations