© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12137
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

    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
    TRAIT
    -1.08
     берегу
    -1.05
    disposing
    -0.94
    สาร
    -0.94
    hemat
    -0.93
     Ảnh
    -0.93
    гъл
    -0.93
     prachtig
    -0.93
    bayern
    -0.93
    endaftar
    -0.91
    POSITIVE LOGITS
    gefügt
    1.12
     recupera
    1.09
     ܕ
    1.07
    tablir
    1.06
     veröffentlicht
    1.01
     apresenta
    1.01
     Übergang
    1.00
     dürfte
    0.99
     perfeitamente
    0.99
    8
    0.97
    Activations Density 0.001%

    No Known Activations