© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32868
    Prev
    Next
    INDEX
    Explanations

    simplifying 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
    Negative Logits
     pensando
    -0.94
    has
    -0.93
     Waren
    -0.87
    el
    -0.87
     sucess
    -0.85
    oy
    -0.85
    怎么可能
    -0.85
     utilised
    -0.84
     umfasst
    -0.83
    }
    -0.83
    POSITIVE LOGITS
     using
    0.98
    botines
    0.95
    жать
    0.95
    nowe
    0.92
     many
    0.91
     aceptas
    0.91
     Infrared
    0.90
     reducing
    0.90
     bluz
    0.90
    phorbia
    0.90
    Activations Density 0.033%

    No Known Activations