© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65757
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     najdete
    -1.05
    がなく
    -1.05
     naszych
    -1.02
     vaše
    -0.99
    があると
    -0.98
    などが
    -0.97
     raczej
    -0.94
    porque
    -0.93
     florales
    -0.93
     būtų
    -0.92
    POSITIVE LOGITS
     another
    0.96
     Dire
    0.87
     '_'
    0.86
     '_
    0.84
     ।
    0.82
     Straßen
    0.81
    `
    0.80
    politik
    0.79
     bija
    0.79
     Ih
    0.78
    Activations Density 0.016%

    No Known Activations