© 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. 130438
    Prev
    Next
    INDEX
    Explanations

    United States court documents, Irish origins

    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
     Drž
    -1.16
    //{
    -1.13
    InSection
    -1.10
    <h2>
    -1.08
     Głów
    -1.07
    CharArray
    -1.01
     []:
    -1.00
     Você
    -1.00
    innerWidth
    -0.96
    NSNotification
    -0.96
    POSITIVE LOGITS
     詩
    1.15
    等級
    1.09
    Zutaten
    1.09
     появится
    1.01
    THINGS
    0.99
    これも
    0.99
     poussière
    0.97
    虽说
    0.97
    ならず
    0.97
     nejen
    0.97
    Activations Density 0.055%

    No Known Activations