© 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. 34-GEMMASCOPE-RES-131K
    7. 99071
    Prev
    Next
    INDEX
    Explanations

    forking child processes

    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_34/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
     férfi
    -0.78
     nấu
    -0.75
    昨天
    -0.73
    ждений
    -0.73
    Composer
    -0.72
     мужа
    -0.69
    getState
    -0.69
    MoveNext
    -0.68
     women
    -0.68
    Лі
    -0.68
    POSITIVE LOGITS
     fork
    1.55
    fork
    1.54
     child
    1.48
     Fork
    1.33
     parent
    1.30
    Fork
    1.27
     Child
    1.20
     Parent
    1.17
     exec
    1.13
     grandchild
    1.13
    Activations Density 0.036%

    No Known Activations