© 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. 99619
    Prev
    Next
    INDEX
    Explanations

    function 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_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
    RETURN
    -1.91
    Return
    -1.90
    returning
    -1.74
    Returning
    -1.63
     returned
    -1.55
     returning
    -1.54
     Return
    -1.52
     Returning
    -1.52
     return
    -1.51
     返回
    -1.49
    POSITIVE LOGITS
    return
    1.48
     than
    1.16
     åren
    1.06
     was
    1.03
     dalamnya
    0.99
     restaurante
    0.99
     been
    0.97
    喱
    0.97
     бывает
    0.96
     Timoteo
    0.95
    Activations Density 0.014%

    No Known Activations