© 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. 71828
    Prev
    Next
    INDEX
    Explanations

    mathematics, ring theory, foliation

    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
    entgen
    -0.99
     pojem
    -0.97
    вропей
    -0.96
     semantics
    -0.93
     Professor
    -0.93
     velikost
    -0.93
    клей
    -0.92
    ierto
    -0.90
    おそ
    -0.90
    liyor
    -0.90
    POSITIVE LOGITS
    옐
    0.96
     hanya
    0.93
     Morm
    0.92
    bones
    0.90
     איז
    0.90
     rios
    0.90
    íteni
    0.89
    íso
    0.88
    ♫
    0.87
     sust
    0.87
    Activations Density 0.027%

    No Known Activations