© 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. 66924
    Prev
    Next
    INDEX
    Explanations

    listing options and criteria

    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
     capot
    -0.86
    seigneur
    -0.85
     couteau
    -0.85
     caoutchouc
    -0.85
    的产品
    -0.83
    nasium
    -0.81
    ığ
    -0.79
     playera
    -0.78
    vaadin
    -0.78
    cire
    -0.78
    POSITIVE LOGITS
     उसे
    1.16
    それを
    1.06
     method
    0.96
     timing
    0.94
     location
    0.85
     quantity
    0.83
     deren
    0.83
     time
    0.82
     їх
    0.82
     methods
    0.80
    Activations Density 0.111%

    No Known Activations