© 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. 129986
    Prev
    Next
    INDEX
    Explanations

    code, questions, and technical descriptions

    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
    ouncement
    -1.20
    voegd
    -1.17
    findViewById
    -1.16
    ==""){
    -1.10
    templateUrl
    -1.10
    änden
    -1.08
    珢
    -1.05
    ನ್
    -1.05
     способности
    -1.05
    ignant
    -1.04
    POSITIVE LOGITS
    Gön
    1.16
     блюдо
    1.15
    kelompok
    0.99
    サイズは
    0.97
    PLE
    0.96
    Fallen
    0.96
    Hadi
    0.95
     рынке
    0.94
    тельстве
    0.94
     seguenti
    0.94
    Activations Density 0.002%

    No Known Activations