© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11186
    Prev
    Next
    INDEX
    Explanations

    code snippets and the word "return"

    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
    のではないか
    -1.11
     essas
    -1.02
    なのでしょう
    -1.00
    を選択します
    -0.94
     soweit
    -0.93
    odziel
    -0.93
    ampiyon
    -0.92
    んだよね
    -0.92
    yfik
    -0.91
    んですよね
    -0.91
    POSITIVE LOGITS
     with
    1.12
    や
    1.07
    で
    1.06
    лее
    1.04
     camiseta
    1.03
     cár
    1.01
     elétrico
    1.00
    siye
    0.97
    ! 
    0.96
    酲
    0.95
    Activations Density 0.002%

    No Known Activations