© 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. 61107
    Prev
    Next
    INDEX
    Explanations

    conditional return statements

    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
    .~\
    -1.73
     火锅
    -1.73
    >'+
    -1.69
    糴
    -1.65
    >>>>>>>
    -1.63
     fria
    -1.63
     插图
    -1.60
     posibil
    -1.59
     flexibles
    -1.59
    ContainsKey
    -1.59
    POSITIVE LOGITS
     or
    2.06
     
    1.89
    ínguez
    1.66
     mantener
    1.63
    などに
    1.62
     Another
    1.61
    ツイン
    1.51
     sostener
    1.50
     terminó
    1.47
     других
    1.45
    Activations Density 0.012%

    No Known Activations