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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 24021
    Prev
    Next
    INDEX
    Explanations

    laws and acts

    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_10/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
    จาก
    -1.45
    wärts
    -1.39
    opropyl
    -1.38
    ffi
    -1.37
     -
    -1.35
     ๆ
    -1.34
    ⇑
    -1.33
     (...)
    -1.33
     first
    -1.33
    čiť
    -1.30
    POSITIVE LOGITS
     :
    1.95
    してくれた
    1.70
     laws
    1.70
     Será
    1.70
     Beobach
    1.69
     law
    1.63
     施工
    1.63
     Aseg
    1.62
     兩
    1.61
     ちゃ
    1.61
    Activations Density 0.045%

    No Known Activations