© 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. 27278
    Prev
    Next
    INDEX
    Explanations

    .cb or .modal or .tab

    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
     INNOV
    -0.92
    easily
    -0.91
     нашла
    -0.89
     gebre
    -0.88
     compl
    -0.86
    יבות
    -0.84
    alers
    -0.84
     selve
    -0.84
    なりに
    -0.84
     akku
    -0.83
    POSITIVE LOGITS
     all
    1.22
     many
    1.11
     ALL
    1.07
     EVERY
    1.05
     after
    1.04
     после
    1.01
     potentially
    0.99
     any
    0.98
     each
    0.98
     non
    0.98
    Activations Density 0.001%

    No Known Activations